This page has only limited features, please log in for full access.
When sufficient time-series images and training data are unavailable for crop classification, features extracted from convolutional neural network (CNN)-based representative learning may not provide useful information to discriminate crops with similar spectral characteristics, leading to poor classification accuracy. In particular, limited input data are the main obstacles to obtain reliable classification results for early crop mapping. This study investigates the potential of a hybrid classification approach, i.e., CNN-random forest (CNN-RF), in the context of early crop mapping, that combines the automatic feature extraction capability of CNN with the superior discrimination capability of an RF classifier. Two experiments on incremental crop classification with unmanned aerial vehicle images were conducted to compare the performance of CNN-RF with that of CNN and RF with respect to the length of the time-series and training data sizes. When sufficient time-series images and training data were used for the classification, the accuracy of CNN-RF was slightly higher or comparable with that of CNN. In contrast, when fewer images and the smallest training data were used at the early crop growth stage, CNN-RF was substantially beneficial and the overall accuracy increased by maximum 6.7%p and 4.6%p in the two study areas, respectively, compared to CNN. This is attributed to its ability to discriminate crops from features with insufficient information using a more sophisticated classifier. The experimental results demonstrate that CNN-RF is an effective classifier for early crop mapping when only limited input images and training samples are available.
Geun-Ho Kwak; Chan-Won Park; Kyung-Do Lee; Sang-Il Na; Ho-Yong Ahn; No-Wook Park. Potential of Hybrid CNN-RF Model for Early Crop Mapping with Limited Input Data. Remote Sensing 2021, 13, 1629 .
AMA StyleGeun-Ho Kwak, Chan-Won Park, Kyung-Do Lee, Sang-Il Na, Ho-Yong Ahn, No-Wook Park. Potential of Hybrid CNN-RF Model for Early Crop Mapping with Limited Input Data. Remote Sensing. 2021; 13 (9):1629.
Chicago/Turabian StyleGeun-Ho Kwak; Chan-Won Park; Kyung-Do Lee; Sang-Il Na; Ho-Yong Ahn; No-Wook Park. 2021. "Potential of Hybrid CNN-RF Model for Early Crop Mapping with Limited Input Data." Remote Sensing 13, no. 9: 1629.
Park, N.-W. and Jang, D.-H., 2020. Geostatistical classification of intertidal surface sediments using log-ratio transformation and high-resolution remote sensing imagery. In: Jung, H.-S.; Lee, S.; Ryu, J.-H., and Cui, T. (eds.), Advances in Geospatial Research of Coastal Environments. Journal of Coastal Research, Special Issue No. 102, pp. 157-165. Coconut Creek (Florida), ISSN 0749-0208.This paper presents a multivariate geostatistical approach to classify intertidal surface sediments by combining compositional data analysis and high-resolution remote sensing imagery. An isometric log-ratio (ilr) transformation is first applied to the sediment composition data prior to employing geostatistical analysis to consider the compositional properties of the sediment compositions. To complement the information deficiency of sparse field measurements, high-resolution remote sensing imagery is considered as exhaustive soft information and integrated with the ilr transformed balances via simple kriging with varying local means (SKLM). An inverse ilr transformation is then applied to the SKLM results to obtain sediment compositions over the study area. Finally, Shepard's classification scheme is applied to the sediment compositions to classify the intertidal surface sediments. A case study was conducted on the Baramarae tidal flats in Korea with high-resolution KOMPSAT-2 imagery to demonstrate the effectiveness of the proposed geostatistical approach. The classification results produced by the integration of high-resolution remote sensing imagery via ilr transformation and SKLM outperformed those based on cokriging of sediment compositions, with an improvement of approximately 11.7 %p in overall accuracy. This improvement was attributed to the superior prediction capability of SKLM for sediment compositions. Further, detailed variations in the sediment distributions in the study area, which could not be observed when using only a limited number of sediment samples, could be revealed by integrating the high-resolution remote sensing imagery. Therefore, the geostatistical integration approach that properly accounts for both the property of sediment compositions and the exhaustive soft information from remote sensing imagery could be effectively applied for the classification of intertidal surface sediments.
No-Wook Park; Dong-Ho Jang. Geostatistical Classification of Intertidal Surface Sediments Using Log-ratio Transformation and High-resolution Remote Sensing Imagery. Journal of Coastal Research 2020, 102, 157 -165.
AMA StyleNo-Wook Park, Dong-Ho Jang. Geostatistical Classification of Intertidal Surface Sediments Using Log-ratio Transformation and High-resolution Remote Sensing Imagery. Journal of Coastal Research. 2020; 102 (sp1):157-165.
Chicago/Turabian StyleNo-Wook Park; Dong-Ho Jang. 2020. "Geostatistical Classification of Intertidal Surface Sediments Using Log-ratio Transformation and High-resolution Remote Sensing Imagery." Journal of Coastal Research 102, no. sp1: 157-165.
As the performance of supervised classification using convolutional neural networks (CNNs) are affected significantly by training patches, it is necessary to analyze the effects of the information content of training patches in patch-based classification. The objective of this study is to quantitatively investigate the effects of class purity of a training patch on performance of crop classification. Here, class purity that refers to a degree of compositional homogeneity of classes within a training patch is considered as a primary factor for the quantification of information conveyed by training patches. New quantitative indices for class homogeneity and variations of local class homogeneity over the study area are presented to characterize the spatial homogeneity of the study area. Crop classification using 2D-CNN was conducted in two regions (Anbandegi in Korea and Illinois in United States) with distinctive spatial distributions of crops and class homogeneity over the area to highlight the effect of class purity of a training patch. In the Anbandegi region with high class homogeneity, superior classification accuracy was obtained when using large size training patches with high class purity (7.1%p improvement in overall accuracy over classification with the smallest patch size and the lowest class purity). Training patches with high class purity could yield a better identification of homogenous crop parcels. In contrast, using small size training patches with low class purity yielded the highest classification accuracy in the Illinois region with low class homogeneity (19.8%p improvement in overall accuracy over classification with the largest patch size and the highest class purity). Training patches with low class purity could provide useful information for the identification of diverse crop parcels. The results indicate that training samples in patch-based classification should be selected based on the class purity that reflects the local class homogeneity of the study area.
Soyeon Park; No-Wook Park. Effects of Class Purity of Training Patch on Classification Performance of Crop Classification with Convolutional Neural Network. Applied Sciences 2020, 10, 3773 .
AMA StyleSoyeon Park, No-Wook Park. Effects of Class Purity of Training Patch on Classification Performance of Crop Classification with Convolutional Neural Network. Applied Sciences. 2020; 10 (11):3773.
Chicago/Turabian StyleSoyeon Park; No-Wook Park. 2020. "Effects of Class Purity of Training Patch on Classification Performance of Crop Classification with Convolutional Neural Network." Applied Sciences 10, no. 11: 3773.
Dense time-series with coarse spatial resolution (DTCS) and sparse time-series with fine spatial resolution (STFS) data often provide complementary information. To make full use of this complementarity, this paper presents a novel spatiotemporal fusion model, the spatial time-series geostatistical deconvolution/fusion model (STGDFM), to generate synthesized dense time-series with fine spatial resolution (DTFS) data. Attributes from the DTCS and STFS data are decomposed into trend and residual components, and the spatiotemporal distributions of these components are predicted through novel schemes. The novelty of STGDFM lies in its ability to (1) consider temporal trend information using land-cover-specific temporal profiles from an entire DTCS dataset, (2) reflect local details of the STFS data using resolution matrix representation, and (3) use residual correction to account for temporary variations or abrupt changes that cannot be modeled from the trend components. The potential of STGDFM is evaluated by conducting extensive experiments that focus on different environments; spatially degraded datasets and real Moderate Resolution Imaging Spectroradiometer (MODIS) and Landsat images are employed. The prediction performance of STGDFM is compared with those of a spatial and temporal adaptive reflectance fusion model (STARFM) and an enhanced STARFM (ESTARFM). Experimental results indicate that STGDFM delivers the best prediction performance with respect to prediction errors and preservation of spatial structures as it captures temporal change information on the prediction date. The superiority of STGDFM is significant when the difference between pair dates and prediction dates increases. These results indicate that STGDFM can be effectively applied to predict DTFS data that are essential for various environmental monitoring tasks.
Yeseul Kim; Phaedon C. Kyriakidis; No-Wook Park. A Cross-Resolution, Spatiotemporal Geostatistical Fusion Model for Combining Satellite Image Time-Series of Different Spatial and Temporal Resolutions. Remote Sensing 2020, 12, 1553 .
AMA StyleYeseul Kim, Phaedon C. Kyriakidis, No-Wook Park. A Cross-Resolution, Spatiotemporal Geostatistical Fusion Model for Combining Satellite Image Time-Series of Different Spatial and Temporal Resolutions. Remote Sensing. 2020; 12 (10):1553.
Chicago/Turabian StyleYeseul Kim; Phaedon C. Kyriakidis; No-Wook Park. 2020. "A Cross-Resolution, Spatiotemporal Geostatistical Fusion Model for Combining Satellite Image Time-Series of Different Spatial and Temporal Resolutions." Remote Sensing 12, no. 10: 1553.
Most infrared satellite remote sensors have a higher spatial resolution than microwave satellite sensors. Microwave satellite remote sensing has proven successful for the retrieval of soil moisture (SM) information. In this study, we propose a SM retrieval algorithm based on temperature vegetation dryness index (TVDI), a function of land surface temperature (LST), and the normalized difference vegetative index (NDVI) provided by Moderate Resolution Imaging Spectroradiometer (MODIS) data. We implemented the LST correction with elevation effect. Conversion relationships between TVDI and SM content for a variety of land types were obtained from spatial and temporal collocation of TVDI and Global Land Data Assimilation System (GLDAS) SM content for 2014. From the comparison with the GLDAS SM for 2015, the proposed TVDI-based SM algorithm showed good performance with CC = 0.609, bias = −0.035 m3/m3, and root-mean-square-error (RMSE) = 0.047 m3/m3, while the Soil Moisture Active Passive (SMAP) and Soil Moisture and Ocean Salinity (SMOS) SMs present CC = 0.637 and 0.741, bias = 0.042 and 0.010 m3/m3, and RMSE = 0.152 and 0.103 m3/m3, respectively. For the in situ SM measurements of the Korea Rural Development Administration (RDA), the proposed TVDI-based SM algorithm yielded CC = 0.556, bias = −0.039 m3/m3, and RMSE = 0.051 m3/m3 excluding the winter season. Consequently, the proposed SM algorithm could contribute to complementing the low spatial resolutions of microwave satellite SM products and low temporal resolutions of GLDAS SM products.
Young-Joo Kwon; Sumin Ryu; Jaeil Cho; Yang-Won Lee; No-Wook Park; Chu-Yong Chung; Sungwook Hong. Infrared Soil Moisture Retrieval Algorithm Using Temperature-Vegetation Dryness Index and Moderate Resolution Imaging Spectroradiometer Data. Asia-Pacific Journal of Atmospheric Sciences 2020, 56, 275 -289.
AMA StyleYoung-Joo Kwon, Sumin Ryu, Jaeil Cho, Yang-Won Lee, No-Wook Park, Chu-Yong Chung, Sungwook Hong. Infrared Soil Moisture Retrieval Algorithm Using Temperature-Vegetation Dryness Index and Moderate Resolution Imaging Spectroradiometer Data. Asia-Pacific Journal of Atmospheric Sciences. 2020; 56 (2):275-289.
Chicago/Turabian StyleYoung-Joo Kwon; Sumin Ryu; Jaeil Cho; Yang-Won Lee; No-Wook Park; Chu-Yong Chung; Sungwook Hong. 2020. "Infrared Soil Moisture Retrieval Algorithm Using Temperature-Vegetation Dryness Index and Moderate Resolution Imaging Spectroradiometer Data." Asia-Pacific Journal of Atmospheric Sciences 56, no. 2: 275-289.
This paper presents a geostatistical simulation approach to not only map the county-level indoor radon concentration (IRC) distributions in South Korea, but also quantify the uncertainty that can be used as decision-supporting information. For county-level IRC mapping in South Korea, environmental factors including geology, radium concentration in surface soil, gravel content in subsoil, and fault line density, which are known to be associated with the source and migration of radon gas, were incorporated into IRC measurements using multi-Gaussian kriging with local means. These four environmental factors could account for about 36% of the variability of noise-filtered IRCs, implying that regional variations of IRCs were affected by these factors. Sequential Gaussian simulation was then applied to generate alternative realizations of county-level IRC distributions. By summarizing the multiple simulation results, we identified some counties that lay on the great limestone series showed elevated IRCs. In addition, there were some counties in which the proportion of grids exceeding the recommended level was high but the uncertainty was also large according to the analysis of several uncertainty measures, which indicates that additional sampling is required for these counties. From the local cluster analysis in conjunction with simulation results, we found that the counties with higher levels of IRC belonged to the statistically significant clusters of high values, and these counties should be the prime targets for radon management and in-depth survey. The geographical distributions of IRC and uncertainty measures presented in this study provide guidance for effective radon management if they are consistently combined with both future IRC measurements and a geogenic radon potential map.
No-Wook Park; Yongjae Kim; Byung-Uck Chang; Geun-Ho Kwak. County-level indoor radon concentration mapping and uncertainty assessment in South Korea using geostatistical simulation and environmental factors. Journal of Environmental Radioactivity 2019, 208-209, 106044 .
AMA StyleNo-Wook Park, Yongjae Kim, Byung-Uck Chang, Geun-Ho Kwak. County-level indoor radon concentration mapping and uncertainty assessment in South Korea using geostatistical simulation and environmental factors. Journal of Environmental Radioactivity. 2019; 208-209 ():106044.
Chicago/Turabian StyleNo-Wook Park; Yongjae Kim; Byung-Uck Chang; Geun-Ho Kwak. 2019. "County-level indoor radon concentration mapping and uncertainty assessment in South Korea using geostatistical simulation and environmental factors." Journal of Environmental Radioactivity 208-209, no. : 106044.
Park, N.-W., 2019. Geostatistical integration of field measurements and multi-sensor remote sensing images for spatial prediction of grain size of intertidal surface sediments. In: Jung, H.-S.; Lee, S.; Ryu, J.-H., and Cui, T. (eds.), Advances in Remote Sensing and Geoscience Information Systems of Coastal Environments. Journal of Coastal Research, Special Issue No. 90, pp. 190-196. Coconut Creek (Florida), ISSN 0749-0208.The objective of this paper is to demonstrate the potential benefit of using high-resolution optical and SAR images for the geostatistical mapping of grain size of intertidal surface sediments. The grain size values from field measurements are integrated with reflectance and backscattering coefficients from multi-sensor images via regression kriging. The trends of grain size variations are estimated using support vector regression (SVR) modeling to account for a nonlinear relationship, and rank transformation is applied to original input variables to highlight the relative differences in input values from multi-sensor images. Unlike the conventional regression-based mapping approach, the residual component that cannot be explained by the multi-sensor remote sensing images is considered and predicted via kriging. The final grain size values are then obtained by adding these two components. From a case study on the Baramarae tidal flats in Korea with KOMPSAT-2 and COSMO-SkyMed images, the integration of multi-sensor images with field measurements via SVR and rank transformation could explain 58 % of grain size variance, leading to a significant improvement in predictive performance (approximately 29 %) over ordinary kriging based on field measurements only. Furthermore, using reflectance and scattering information from multi-sensor images generated the grain size distribution with more detailed variations in the study area. Therefore, the synergistic use of multi-sensor images within an advanced geostatistical integration framework is expected to be very effective for the reliable mapping of the grain size of intertidal surface sediments when only a limited number of field measurements are available.
No-Wook Park. Geostatistical Integration of Field Measurements and Multi-Sensor Remote Sensing Images for Spatial Prediction of Grain Size of Intertidal Surface Sediments. Journal of Coastal Research 2019, 90, 190 -196.
AMA StyleNo-Wook Park. Geostatistical Integration of Field Measurements and Multi-Sensor Remote Sensing Images for Spatial Prediction of Grain Size of Intertidal Surface Sediments. Journal of Coastal Research. 2019; 90 (sp1):190-196.
Chicago/Turabian StyleNo-Wook Park. 2019. "Geostatistical Integration of Field Measurements and Multi-Sensor Remote Sensing Images for Spatial Prediction of Grain Size of Intertidal Surface Sediments." Journal of Coastal Research 90, no. sp1: 190-196.
Satellite-based remote sensing techniques have been widely used to monitor droughts spanning large areas. Various agricultural drought indices have been developed to assess the intensity of agricultural drought and to detect damaged crop areas. However, to better understand the responses of agricultural drought to meteorological drought, agricultural management practices should be taken into consideration. This study aims to evaluate the responses to drought under different forms of agricultural management for the extreme drought that occurred on the Korean Peninsula in 2014 and 2015. The 3-month standardized precipitation index (SPI3) and the 3-month vegetation health index (VHI3) were selected as a meteorological drought index and an agricultural drought index, respectively. VHI3, which comprises the 3-month temperature condition index (TCI3) and the 3-month vegetation condition index (VCI3), differed significantly in the study area during the extreme drought. VCI3 had a different response to the lack of precipitation in South and North Korea because it was affected by irrigation. However, the time series of TCI3 were similar in South and North Korea. These results meant that each drought index has different characteristics and should be utilized with caution. Our results are expected to help comprehend the responses of the agricultural drought index on meteorological drought depending on agricultural management.
Jae-Hyun Ryu; Kyung-Soo Han; Yang-Won Lee; No-Wook Park; Sungwook Hong; Chu-Yong Chung; Jaeil Cho. Different Agricultural Responses to Extreme Drought Events in Neighboring Counties of South and North Korea. Remote Sensing 2019, 11, 1773 .
AMA StyleJae-Hyun Ryu, Kyung-Soo Han, Yang-Won Lee, No-Wook Park, Sungwook Hong, Chu-Yong Chung, Jaeil Cho. Different Agricultural Responses to Extreme Drought Events in Neighboring Counties of South and North Korea. Remote Sensing. 2019; 11 (15):1773.
Chicago/Turabian StyleJae-Hyun Ryu; Kyung-Soo Han; Yang-Won Lee; No-Wook Park; Sungwook Hong; Chu-Yong Chung; Jaeil Cho. 2019. "Different Agricultural Responses to Extreme Drought Events in Neighboring Counties of South and North Korea." Remote Sensing 11, no. 15: 1773.
A geostatistical framework for spatial quality assessment framework of coarse resolution remote sensing products is presented that can account for either the scale difference or the uncertainty of reference value prediction at coarse resolutions. A set of multiple reference field realizations is first generated at a fine spatial resolution using geostatistical simulation to explore the uncertainty in the true unknown reference field. The upscaling of multiple reference field realizations to coarse resolution is then followed to match the spatial resolution of the target remote sensing product and create coarse resolution reference fields. The simulated reference values at each coarse pixel are compared to the corresponding reported value from the coarse resolution remote sensing product, yielding alternative error values, from which several location-dependent statistics such as mean error, mean absolute error, and probability of overestimation can be computed. An experiment involving monthly Tropical Rainfall Measuring Mission (TRMM) precipitation products and point-level rain gauge data over South Korea illustrates the applicability of the proposed approach. The spatially distributed error statistics are useful to identify areas with larger errors and the degree of overestimation in the study area, leading to the identification of areas with unreliable estimates within the TRMM precipitation products. Therefore, it is expected that the geostatistical assessment framework presented in this paper can be effectively used to evaluate the spatial quality of coarse resolution remote sensing products.
No-Wook Park; Phaedon C. Kyriakidis. A Geostatistical Approach to Spatial Quality Assessment of Coarse Spatial Resolution Remote Sensing Products. Journal of Sensors 2019, 2019, 1 -14.
AMA StyleNo-Wook Park, Phaedon C. Kyriakidis. A Geostatistical Approach to Spatial Quality Assessment of Coarse Spatial Resolution Remote Sensing Products. Journal of Sensors. 2019; 2019 ():1-14.
Chicago/Turabian StyleNo-Wook Park; Phaedon C. Kyriakidis. 2019. "A Geostatistical Approach to Spatial Quality Assessment of Coarse Spatial Resolution Remote Sensing Products." Journal of Sensors 2019, no. : 1-14.
The international symposium on remote sensing 2018 (ISRS 2018) was held in Pyeongchang, Korea, 9–11 May 2018
Hyung-Sup Jung; Joo-Hyung Ryu; Sang-Eun Park; Hoonyol Lee; No-Wook Park. Special Issue on Selected Papers from the “International Symposium on Remote Sensing 2018”. Remote Sensing 2019, 11, 1439 .
AMA StyleHyung-Sup Jung, Joo-Hyung Ryu, Sang-Eun Park, Hoonyol Lee, No-Wook Park. Special Issue on Selected Papers from the “International Symposium on Remote Sensing 2018”. Remote Sensing. 2019; 11 (12):1439.
Chicago/Turabian StyleHyung-Sup Jung; Joo-Hyung Ryu; Sang-Eun Park; Hoonyol Lee; No-Wook Park. 2019. "Special Issue on Selected Papers from the “International Symposium on Remote Sensing 2018”." Remote Sensing 11, no. 12: 1439.
This paper compares different artificial intelligence (AI) models in order to develop the best crop yield prediction model for the Midwestern United States (US). Through experiments to examine the effects of phenology using three different periods, we selected the July–August (JA) database as the best months to predict corn and soybean yields. Six different AI models for crop yield prediction are tested in this research. Then, a comprehensive and objective comparison is conducted between the AI models. Particularly for the deep neural network (DNN) model, we performed an optimization process to ensure the best configurations for the layer structure, cost function, optimizer, activation function, and drop-out ratio. In terms of mean absolute error (MAE), our DNN model with the JA database was approximately 21–33% and 17–22% more accurate for corn and soybean yields, respectively, than the other five AI models. This indicates that corn and soybean yields for a given year can be forecasted in advance, at the beginning of September, approximately a month or more ahead of harvesting time. A combination of the optimized DNN model and spatial statistical methods should be investigated in future work, to mitigate partly clustered errors in some regions.
Nari Kim; Kyung-Ja Ha; No-Wook Park; Jaeil Cho; Sungwook Hong; Yang-Won Lee. A Comparison Between Major Artificial Intelligence Models for Crop Yield Prediction: Case Study of the Midwestern United States, 2006–2015. ISPRS International Journal of Geo-Information 2019, 8, 240 .
AMA StyleNari Kim, Kyung-Ja Ha, No-Wook Park, Jaeil Cho, Sungwook Hong, Yang-Won Lee. A Comparison Between Major Artificial Intelligence Models for Crop Yield Prediction: Case Study of the Midwestern United States, 2006–2015. ISPRS International Journal of Geo-Information. 2019; 8 (5):240.
Chicago/Turabian StyleNari Kim; Kyung-Ja Ha; No-Wook Park; Jaeil Cho; Sungwook Hong; Yang-Won Lee. 2019. "A Comparison Between Major Artificial Intelligence Models for Crop Yield Prediction: Case Study of the Midwestern United States, 2006–2015." ISPRS International Journal of Geo-Information 8, no. 5: 240.
Unmanned aerial vehicle (UAV) images that can provide thematic information at much higher spatial and temporal resolutions than satellite images have great potential in crop classification. Due to the ultra-high spatial resolution of UAV images, spatial contextual information such as texture is often used for crop classification. From a data availability viewpoint, it is not always possible to acquire time-series UAV images due to limited accessibility to the study area. Thus, it is necessary to improve classification performance for situations when a single or minimum number of UAV images are available for crop classification. In this study, we investigate the potential of gray-level co-occurrence matrix (GLCM)-based texture information for crop classification with time-series UAV images and machine learning classifiers including random forest and support vector machine. In particular, the impact of combining texture and spectral information on the classification performance is evaluated for cases that use only one UAV image or multi-temporal images as input. A case study of crop classification in Anbandegi of Korea was conducted for the above comparisons. The best classification accuracy was achieved when multi-temporal UAV images which can fully account for the growth cycles of crops were combined with GLCM-based texture features. However, the impact of the utilization of texture information was not significant. In contrast, when one August UAV image was used for crop classification, the utilization of texture information significantly affected the classification performance. Classification using texture features extracted from GLCM with larger kernel size significantly improved classification accuracy, an improvement of 7.72%p in overall accuracy for the support vector machine classifier, compared with classification based solely on spectral information. These results indicate the usefulness of texture information for classification of ultra-high-spatial-resolution UAV images, particularly when acquisition of time-series UAV images is difficult and only one UAV image is used for crop classification.
Geun-Ho Kwak; No-Wook Park. Impact of Texture Information on Crop Classification with Machine Learning and UAV Images. Applied Sciences 2019, 9, 643 .
AMA StyleGeun-Ho Kwak, No-Wook Park. Impact of Texture Information on Crop Classification with Machine Learning and UAV Images. Applied Sciences. 2019; 9 (4):643.
Chicago/Turabian StyleGeun-Ho Kwak; No-Wook Park. 2019. "Impact of Texture Information on Crop Classification with Machine Learning and UAV Images." Applied Sciences 9, no. 4: 643.
The worst forest fire in South Korea occurred in April 2000 on the eastern coast. Forest recovery works were conducted until 2005, and the forest has been monitored since the fire. Remote sensing techniques have been used to detect the burned areas and to evaluate the recovery-time point of the post-fire processes during the past 18 years. We used three indices, Normalized Burn Ratio (NBR), Normalized Difference Vegetation Index (NDVI), and Gross Primary Production (GPP), to temporally monitor a burned area in terms of its moisture condition, vegetation biomass, and photosynthetic activity, respectively. The change of those three indices by forest recovery processes was relatively analyzed using an unburned reference area. The selected unburned area had similar characteristics to the burned area prior to the forest fire. The temporal patterns of NBR and NDVI, not only showed the forest recovery process as a result of forest management, but also statistically distinguished the recovery periods at the regions of low, moderate, and high fire severity. The NBR2.1 for all areas, calculated using 2.1 μm wavelengths, reached the unburned state in 2008. The NDVI for areas with low and moderate fire severity levels became significantly equal to the unburned state in 2009 (p > 0.05), but areas with high severity levels did not reach the unburned state until 2017. This indicated that the surface and vegetation moisture conditions recovered to the unburned state about 8 years after the fire event, while vegetation biomass and health required a longer time to recover, particularly for high severity regions. In the case of GPP, it rapidly recovered after about 3 years. Then, the steady increase in GPP surpassed the GPP of the reference area in 2015 because of the rapid growth and high photosynthetic activity of young forests. Therefore, the concluding scientific message is that, because the recovery-time point for each component of the forest ecosystem is different, using only one satellite-based indicator will not be suitable to understand the post-fire recovery process. NBR, NDVI, and GPP can be combined. Further studies will require more approaches using various terms of indices.
Jae-Hyun Ryu; Kyung-Soo Han; Sungwook Hong; No-Wook Park; Yang-Won Lee; Jaeil Cho. Satellite-Based Evaluation of the Post-Fire Recovery Process from the Worst Forest Fire Case in South Korea. Remote Sensing 2018, 10, 918 .
AMA StyleJae-Hyun Ryu, Kyung-Soo Han, Sungwook Hong, No-Wook Park, Yang-Won Lee, Jaeil Cho. Satellite-Based Evaluation of the Post-Fire Recovery Process from the Worst Forest Fire Case in South Korea. Remote Sensing. 2018; 10 (6):918.
Chicago/Turabian StyleJae-Hyun Ryu; Kyung-Soo Han; Sungwook Hong; No-Wook Park; Yang-Won Lee; Jaeil Cho. 2018. "Satellite-Based Evaluation of the Post-Fire Recovery Process from the Worst Forest Fire Case in South Korea." Remote Sensing 10, no. 6: 918.
To improve the accuracy of classification with a small amount of training data, this paper presents a self-learning approach that defines class labels from sequential patterns using a series of past land-cover maps. By stacking past land-cover maps, unique sequence rule information from sequential change patterns of land-covers is first generated, and a rule-based class label image is then prepared for a given time. After the most informative pixels with high uncertainty are selected from the initial classification, rule-based class labels are assigned to the selected pixels. These newly labeled pixels are added to training data, which then undergo an iterative classification process until a stopping criterion is reached. Time-series MODIS NDVI data sets and cropland data layers (CDLs) from the past five years are used for the classification of various crop types in Kansas. From the experiment results, it is found that once the rule-based labels are derived from past CDLs, the labeled informative pixels could be properly defined without analyst intervention. Regardless of different combinations of past CDLs, adding these labeled informative pixels to training data increased classification accuracy and the maximum improvement of 8.34 percentage points in overall accuracy was achieved when using three CDLs, compared to the initial classification result using a small amount of training data. Using more than three consecutive CDLs showed slightly better classification accuracy than when using two CDLs (minimum and maximum increases were 1.56 and 2.82 percentage points, respectively). From a practical viewpoint, using three or four CDLs was the best choice for this study area. Based on these experiment results, the presented approach could be applied effectively to areas with insufficient training data but access to past land-cover maps. However, further consideration should be given to select the optimal number of past land-cover maps and reduce the impact of errors of rule-based labels.
Yeseul Kim; No-Wook Park; Kyung-Do Lee. Self-Learning Based Land-Cover Classification Using Sequential Class Patterns from Past Land-Cover Maps. Remote Sensing 2017, 9, 921 .
AMA StyleYeseul Kim, No-Wook Park, Kyung-Do Lee. Self-Learning Based Land-Cover Classification Using Sequential Class Patterns from Past Land-Cover Maps. Remote Sensing. 2017; 9 (9):921.
Chicago/Turabian StyleYeseul Kim; No-Wook Park; Kyung-Do Lee. 2017. "Self-Learning Based Land-Cover Classification Using Sequential Class Patterns from Past Land-Cover Maps." Remote Sensing 9, no. 9: 921.
Heavy summer rainfall is a primary natural disaster affecting lives and properties in the Korean Peninsula. This study presents a satellite-based rainfall rate retrieval algorithm for the South Korea combining polarization-corrected temperature (PCT) and scattering index (SI) data from the 36.5 and 89.0 GHz channels of the Advanced microwave Scanning Radiometer 2 (AMSR-2) onboard the Global Change Observation Mission (GCOM)-W1 satellite. The coefficients for the algorithm were obtained from spatial and temporal collocation data from the AMSR-2 and groundbased automatic weather station rain gauges from 1 July - 30 August during the years, 2012-2015. There were time delays of about 25 minutes between the AMSR-2 observations and the ground raingauge measurements. A new linearly-combined rainfall retrieval algorithm focused on heavy rain for the PCT and SI was validated using ground-based rainfall observations for the South Korea from 1 July - 30 August, 2016. The validation presented PCT and SI methods showed slightly improved results for rainfall > 5 mm h-1 compared to the current ASMR-2 level 2 data. The best bias and root mean square error (RMSE) for the PCT method at AMSR-2 36.5 GHz were 2.09 mm h-1 and 7.29 mm h-1, respectively, while the current official AMSR-2 rainfall rates show a larger bias and RMSE (4.80 mm h-1 and 9.35 mm h-1, respectively). This study provides a scatteringbased over-land rainfall retrieval algorithm for South Korea affected by stationary front rain and typhoons with the advantages of the previous PCT and SI methods to be applied to a variety of spaceborne passive microwave radiometers.
Young-Joo Kwon; Hayan Shin; Hyunju Ban; Yang-Won Lee; Kyung-Ae Park; Jaeil Cho; No-Wook Park; Sungwook Hong. A scattering-based over-land rainfall retrieval algorithm for South Korea using GCOM-W1/AMSR-2 data. Asia-Pacific Journal of Atmospheric Sciences 2017, 53, 385 -392.
AMA StyleYoung-Joo Kwon, Hayan Shin, Hyunju Ban, Yang-Won Lee, Kyung-Ae Park, Jaeil Cho, No-Wook Park, Sungwook Hong. A scattering-based over-land rainfall retrieval algorithm for South Korea using GCOM-W1/AMSR-2 data. Asia-Pacific Journal of Atmospheric Sciences. 2017; 53 (3):385-392.
Chicago/Turabian StyleYoung-Joo Kwon; Hayan Shin; Hyunju Ban; Yang-Won Lee; Kyung-Ae Park; Jaeil Cho; No-Wook Park; Sungwook Hong. 2017. "A scattering-based over-land rainfall retrieval algorithm for South Korea using GCOM-W1/AMSR-2 data." Asia-Pacific Journal of Atmospheric Sciences 53, no. 3: 385-392.
This paper compared and evaluated the effects of explanatory power of regression models on predictive performance in component decomposition-based downscaling of coarse scale precipitation products. The regression models applied in this paper include (1) multiple linear regression (MLR), (2) geographically weighted regression (GWR), and (3) random forest (RF). From a case study of spatial downscaling of TRMM monthly precipitation products in South Korea, it was observed that GWR showed the highest explanatory power, followed by RF and MLR. From evaluation with independent rain gauge data, GWR-based downscaling outperformed other regression models. However, MLR-based downscaling with the lowest explanatory power showed better predictive performance than RF-based downscaling. Furthermore, the RF-based downscaling results could not preserve the overall patterns of original TRMM products. The GWR-based downscaling with the superior predictive performance included noisy artifacts in the downscaling result, which may be explained by over-fitting to the original coarse scale data. Thus, high explanatory power of regression models does not always improve predictive performance and it is suggested that other measures such as the preservation of spatial patterns of original coarse scale data should be considered for evaluation of downscaling results.
Yeseul Kim; No-Wook Park. Comparison of regression models for spatial downscaling of coarse scale satellite-based precipitation products. 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) 2017, 4634 -4637.
AMA StyleYeseul Kim, No-Wook Park. Comparison of regression models for spatial downscaling of coarse scale satellite-based precipitation products. 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS). 2017; ():4634-4637.
Chicago/Turabian StyleYeseul Kim; No-Wook Park. 2017. "Comparison of regression models for spatial downscaling of coarse scale satellite-based precipitation products." 2017 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) , no. : 4634-4637.
Indoor radon is the second most important risk factor for lung cancer and may also be a risk factor for hematopoietic cancers, particularly in children and adolescents. The present study measured indoor radon concentration nationwide at 5553 points during 1989–2009 and spatially interpolated using lognormal kriging. The incidences of lung cancer, non-Hodgkin’s lymphoma (NHL), and leukemia, stratified by sex and five-year age groups in each of the 234 administrative regions in the country during 1999–2008, were obtained from the National Cancer Registry and used to calculate the standardized incidence ratios. After considering regional deprivation index values and smoking rates by sex in each region as confounding variables, the cancer risks were estimated based on Bayesian hierarchical modeling. We found that a 10 Bq/m3 increase in indoor radon concentration was associated with a 1% increase in the incidence of lung cancer in male and a 7% increase in NHL in female children and adolescents in Korea aged less than 20 years. Leukemia was not associated with indoor radon concentration. The increase in NHL risk among young women requires confirmation in future studies, and the radon control program should consider children and adolescents.
Mina Ha; Seung-Sik Hwang; Sungchan Kang; No-Wook Park; Byung-Uck Chang; Yongjae Kim. Geographical Correlations between Indoor Radon Concentration and Risks of Lung Cancer, Non-Hodgkin’s Lymphoma, and Leukemia during 1999–2008 in Korea. International Journal of Environmental Research and Public Health 2017, 14, 344 .
AMA StyleMina Ha, Seung-Sik Hwang, Sungchan Kang, No-Wook Park, Byung-Uck Chang, Yongjae Kim. Geographical Correlations between Indoor Radon Concentration and Risks of Lung Cancer, Non-Hodgkin’s Lymphoma, and Leukemia during 1999–2008 in Korea. International Journal of Environmental Research and Public Health. 2017; 14 (4):344.
Chicago/Turabian StyleMina Ha; Seung-Sik Hwang; Sungchan Kang; No-Wook Park; Byung-Uck Chang; Yongjae Kim. 2017. "Geographical Correlations between Indoor Radon Concentration and Risks of Lung Cancer, Non-Hodgkin’s Lymphoma, and Leukemia during 1999–2008 in Korea." International Journal of Environmental Research and Public Health 14, no. 4: 344.
This paper investigates the benefits of integrating coarse resolution satellite-derived precipitation estimates with quasi-point rain gauge data for generating a fine spatial resolution precipitation map product. To integrate the two precipitation data sources, a geostatistical downscaling and integration approach is presented that can account for the differences in spatial resolution between data from different supports and adjusts inherent errors in the coarse resolution precipitation estimates. First, coarse resolution precipitation estimates are downscaled at a fine spatial resolution via area-to-point kriging to allow direct comparison with rain gauge data. Second, the downscaled precipitation estimates are integrated with the rain gauge data by multivariate kriging. In particular, errors in the coarse resolution precipitation estimates are adjusted against rain gauge data during this second stage. In this study, simple kriging with local means (SKLM) and kriging with an external drift (KED) are used as multivariate kriging algorithms. For comparative purposes, conditional merging (CM), a frequently-applied method for integrating rain gauge data and radar precipitation, is also employed. From a case study with Tropical Rainfall Measuring Mission (TRMM) 3B43 monthly precipitation products acquired in South Korea from May–October in 2013, we found that the incorporation of TRMM data with rain gauge data did not improve prediction performance when the number of rain gauge data was relatively large. However, the benefit of integrating TRMM and rain gauge data was most striking, regardless of multivariate kriging algorithms, when a small number of rain gauge data was used. These results indicate that the coarse resolution satellite-derived precipitation product would be a useful source for mapping precipitation at a fine spatial resolution if the geostatistical integration approach is applied to areas with sparse rain gauges.
No-Wook Park; Phaedon C. Kyriakidis; Sungwook Hong. Geostatistical Integration of Coarse Resolution Satellite Precipitation Products and Rain Gauge Data to Map Precipitation at Fine Spatial Resolutions. Remote Sensing 2017, 9, 255 .
AMA StyleNo-Wook Park, Phaedon C. Kyriakidis, Sungwook Hong. Geostatistical Integration of Coarse Resolution Satellite Precipitation Products and Rain Gauge Data to Map Precipitation at Fine Spatial Resolutions. Remote Sensing. 2017; 9 (3):255.
Chicago/Turabian StyleNo-Wook Park; Phaedon C. Kyriakidis; Sungwook Hong. 2017. "Geostatistical Integration of Coarse Resolution Satellite Precipitation Products and Rain Gauge Data to Map Precipitation at Fine Spatial Resolutions." Remote Sensing 9, no. 3: 255.
Impact of Trend Estimates on Predictive Performance in Model Evaluation for Spatial Downscaling of Satellite-based Precipitation Data Downscaling;Precipitation;Regression;Trend component; Spatial downscaling with fine resolution auxiliary variables has been widely applied to predict precipitation at fine resolution from coarse resolution satellite-based precipitation products. The spatial downscaling framework is usually based on the decomposition of precipitation values into trend and residual components. The fine resolution auxiliary variables contribute to the estimation of the trend components. The main focus of this study is on quantitative analysis of impacts of trend component estimates on predictive performance in spatial downscaling. Two regression models were considered to estimate the trend components: multiple linear regression (MLR) and geographically weighted regression (GWR). After estimating the trend components using the two models,residual components were predicted at fine resolution grids using area-to-point kriging. Finally, the sum of the trend and residual components were considered as downscaling results. From the downscaling experiments with time-series Tropical Rainfall Measuring Mission (TRMM) 3B43 precipitation data, MLR-based downscaling showed the similar or even better predictive performance, compared with GWR-based downscaling with very high explanatory power. Despite very high explanatory power of GWR, the relationships quantified from TRMM precipitation data with errors and the auxiliary variables at coarse resolution may exaggerate the errors in the trend components at fine resolution. As a result, the errors attached to the trend estimates greatly affected the predictive performance. These results indicate that any regression model with high explanatory power does not always improve predictive performance due to intrinsic errors of the input coarse resolution data. Thus, it is suggested that the explanatory power of trend estimation models alone cannot be always used for the selection of an optimal model in spatial downscaling with fine resolution auxiliary variables.
Yeseul Kim; No-Wook Park. Impact of Trend Estimates on Predictive Performance in Model Evaluation for Spatial Downscaling of Satellite-based Precipitation Data. Korean Journal of Remote Sensing 2017, 33, 25 -35.
AMA StyleYeseul Kim, No-Wook Park. Impact of Trend Estimates on Predictive Performance in Model Evaluation for Spatial Downscaling of Satellite-based Precipitation Data. Korean Journal of Remote Sensing. 2017; 33 (1):25-35.
Chicago/Turabian StyleYeseul Kim; No-Wook Park. 2017. "Impact of Trend Estimates on Predictive Performance in Model Evaluation for Spatial Downscaling of Satellite-based Precipitation Data." Korean Journal of Remote Sensing 33, no. 1: 25-35.
A simple approach was developed to predict corn yields using the MoDerate Resolution Imaging Spectroradiometer (MODIS) data product from two geographically separate major corn crop production regions: Illinois, USA and Heilongjiang, China. The MOD09A1 data, which are eight-day interval surface reflectance data, were obtained from day of the year (DOY) 89 to 337 to calculate the leaf area index (LAI). The sum of the LAI from early in the season to a given date in the season (end of DOY (EOD)) was well fitted to a logistic function and represented seasonal changes in leaf area duration (LAD). A simple phenology model was derived to estimate the dates of emergence and maturity using the LAD-logistic function parameters b1 and b2, which represented the rate of increase in LAI and the date of maximum LAI, respectively. The phenology model predicted emergence and maturity dates fairly well, with root mean square error (RMSE) values of 6.3 and 4.9 days for the validation dataset, respectively. Two simple linear regression models (YP and YF) were established using LAD as the variable to predict corn yield. The yield model YP used LAD from predicted emergence to maturity, and the yield model YF used LAD for a predetermined period from DOY 89 to a particular EOD. When state/province corn yields for the validation dataset were predicted at DOY 321, near completion of the corn harvest, the YP model, including the predicted phenology, performed much better than the YF model, with RMSE values of 0.68 t/ha and 0.66 t/ha for Illinois and Heilongjiang, respectively. The YP model showed similar or better performance, even for the much earlier pre-harvest yield prediction at DOY 257. In addition, the model performance showed no difference between the two study regions with very different climates and cultivation methods, including cultivar and irrigation management. These results suggested that the approach described in this paper has potential for application to relatively wide agroclimatic regions with different cultivation methods and for extension to the other crops. However, it needs to be examined further in tropical and sub-tropical regions, which are very different from the two study regions with respect to agroclimatic constraints and agrotechnologies.
Ho-Young Ban; Kwang Soo Kim; No-Wook Park; Byun-Woo Lee. Using MODIS Data to Predict Regional Corn Yields. Remote Sensing 2016, 9, 16 .
AMA StyleHo-Young Ban, Kwang Soo Kim, No-Wook Park, Byun-Woo Lee. Using MODIS Data to Predict Regional Corn Yields. Remote Sensing. 2016; 9 (1):16.
Chicago/Turabian StyleHo-Young Ban; Kwang Soo Kim; No-Wook Park; Byun-Woo Lee. 2016. "Using MODIS Data to Predict Regional Corn Yields." Remote Sensing 9, no. 1: 16.