13 February 2017 in Geocarto International
This study developed an approach to map rice-cropping systems in An Giang and Dong Thap provinces, South Vietnam using multi-temporal Sentinel-1A (S1A) data. The data were processed through four steps: (1) data pre-processing, (2) constructing smooth time series VH backscatter data, (3) rice crop classification using random forests (RF) and support vector machines (SVM) and (4) accuracy assessment. The results indicated that the smooth VH backscatter profiles reflected the temporal characteristics of rice-cropping patterns in the study region. The comparisons between the classification results and the ground reference data indicated that the overall accuracy and Kappa coefficient achieved from RF were 86.1% and 0.72, respectively, which were slightly more accurate than SVM (overall accuracy of 83.4% and Kappa coefficient of 0.67). These results were reaffirmed by the government’s rice area statistics with the relative error in area (REA) values of 0.2 and 2.2% for RF and SVM, respectively.
15 August 2020 in International Journal of Remote Sensing
Rice is the most important food crop in Taiwan, directly feeding more than 23 million people in the country. Information on rice production is thus crucial for crop management and food policymaking. This study aims to develop a machine learning (ML) approach for predicting rice crop yields in Taiwan using time-series Moderate Resolution Imaging Spectroradiometer (MODIS) data. We processed the data for the period from 2000 to 2018, following three main steps: (1) data pre-processing to generate smooth time-series Normalized Difference Vegetation Index (NDVI) data, (2) establishment of models for yield predictions using the heading date (HD) NDVI value, and the accumulated NDVI value of the dates from heading to maturity (DHM). The data from 2000 to 2017 were used for building predictive models using the random forests (RF) and support vector machines (SVM), leaving the 2018 data for model assessment, and (3) evaluation of model performance. The results compared with the government’s yield statistics indicated good predictions, with the root mean square error (RMSE) and mean absolute error (MAE) values between 7.1% and 11.8%, and Willmott’s index of agreement (d) values between 0.81 and 0.84 for the first crop, and 5.6% and 11.3% and d values between 0.91 and 0.95 for the second crop, respectively. A slight underestimation of yield predictions was observed for both crops, with the relative error (RE) values of −6.5% to −8.2% and −3.8% to −6% for the first and second crops, respectively. The results of regression analysis also confirmed a close agreement between these two datasets, with the correlation coefficient (r) higher than 0.84 (p-value <0.05), in both cases. Although some factors, including mixed-pixel issues, boundary effects, and cloud cover potentially affected the modelling results, our study demonstrated the effectiveness of ML methods for regional rice yield predictions from MODIS NDVI data in Taiwan.
7 January 2021 in International Journal of Remote Sensing
Spatial assessment of rice-cultivated areas is a crucial activity in Taiwan due to government initiatives to provide policymakers with reliable and timely information for devising successful rice grain import and export plans. The objective of this study is to develop a phenological object-based approach for collectively mapping patches of rice fields using the time-series Sentinel-1 Synthetic Aperture Radar (SAR) data. We processed the data for 2019 cropping seasons, following three main steps: (1) data pre-processing to construct the smooth twelve-day time-series composite vertical transmit and horizontal receive (VH) polarized data, (2) object-based image classification of rice-cultivated areas using phenological metrics, and (3) accuracy assessment of the mapping results. The classification maps compared with the government’s ground reference maps indicated satisfactory accuracies, with producer’s accuracies of 84.2% and 82.6% and user’s accuracies of 82.1% and 85.3% for the first and second crops, respectively. These results were reaffirmed by close agreement in area estimates between the satellite-derived rice area and government’s reference data at township level, with coefficient of determination (R2) values of 0.96 and 0.94 for the first and second crops, respectively. In spite of some error sources, including mixed-pixel issues and edge effects, that lowered the mapping accuracy, the results of this study have demonstrated that our mapping approach using the time-series Sentinel-1 VH data and information of crop phenology could be potentially applied at a larger scale in Taiwan and transferable to other regions for updating rice crop maps on a timely and frequent basis.
31 August 2016 in Geomatics, Natural Hazards and Risk
Drought is the most pressing problem facing farmers in Central America, and information on drought is thus crucial for agronomic planners to minimize impacts on crop production and food supply. This study assessed the cultivated areas affected by droughts using the Moderate Resolution Imaging Spectroradiometer (MODIS) data during 2001–2014, processed using a simple vegetation health index (VHI). The results, verified with the Advanced Microwave Scanning Radiometer 2 (AMSR2) precipitation data and TVDI (temperature vegetation dryness index), indicated that the correlation coefficients (r) between the VHI and AMSR2 precipitation data for 2013 and 2014 were 0.81 and 0.78, respectively, and the values between VHI and TVDI were –0.68 and –0.61, respectively. The largest area of severe drought was especially observed for the 2014 primera season (April–August) over the last 14 years. The drought mapping results were aggregated with the cultivated areas for crop monitoring purposes.
26 June 2019 in Geocarto International
This study aims to develop an approach for flood assessment using MODIS data in Cambodia. The data were processed for the period from 2000 to 2017 using vegetation and water surface indices. The results of flood mapping were verified with the ground reference data, indicating the overall accuracy of 88.7% and Kappa coefficient of 0.77, respectively. These findings were confirmed by close agreement between the flood-mapping area and ground reference data, with the correlation coefficient of determination (R2) of 0.94. The flood-prone areas were generally concentrated along the Mekong River and Tonle Sap Lake. The seasonal flooded areas observed for 2010, 2015, and 2016 were remarkably smaller than other years, mainly attributed to the El Niño weather phenomenon exacerbated by impacts of climate change. Eventually, the probability of flood occurrence during this 18-year period with reference to percentage of population at the district level was calculated for flood-management purposes.
4 June 2018 in Geocarto International
MMMario Giovanni Molina Masferrer
Mario Giovanni Molina Masferrer
LRLuis Eduardo Menjívar Recinos
Luis Eduardo Menjívar Recinos
This study aims to develop an approach to characterize cropland drought conditions in El Salvador, Central America. The data were processed for 2016–2017 through three main steps: (1) reconstructing MODIS land-surface temperature (LST), (2) Landsat-MODIS data fusion and (3) drought delineation using the temperature vegetation dryness index (TVDI). The results of LST reconstruction using the random forests (RF) indicated the median RMSE value of 0.5 °C. The fusion results achieved from the STARFM compared with the reference Landsat data revealed close agreement with the correlation coefficient (r) values higher than 0.84. The TVDI results verified with that from the reference Landsat data indicated r values of 0.85 and 0.75 for 2016 and 2017, respectively. The larger very dry area was observed for the 2016 primera season due to prolonged droughts. Approximately 11.5% and 10.7% of croplands were, respectively, associated with very dry moisture condition in the 2016 and 2017 primera seasons.