This page has only limited features, please log in for full access.
The increasing availability of satellite data at higher spatial, temporal and spectral resolutions is enabling new applications in agriculture and economic development, including agricultural insurance. Yet, effectively using satellite data in this context requires blending technical knowledge about their capabilities and limitations with an understanding of their influence on the value of risk-reduction programmes. In this Review, we discuss how approaches to estimate agricultural losses for index insurance have evolved from costly field-sampling-based campaigns towards lower-cost techniques using weather and satellite data. We identify advances in remote sensing and crop modelling for assessing agricultural conditions, but reliably and cheaply assessing production losses remains challenging in complex landscapes. We illustrate how an economic framework can be used to gauge and enhance the value of insurance based on earth-observation data, emphasizing that even as yield-estimation techniques improve, the value of an index insurance contract for the insured depends largely on how well it captures the losses when people suffer most. Strategically improving the collection and accessibility of reliable ground-reference data on crop types and production would facilitate this task. Audits to account for inevitable misestimation complement efforts to detect and protect against large losses. Improvements in earth observation are enabling new approaches to assess agricultural losses, such as those resulting from adverse weather. This Review examines advances in the application of remotely sensed data and crop modelling in index-based insurance as well as opportunities to enhance the quality of index insurance programmes.
Elinor Benami; Zhenong Jin; Michael R. Carter; Aniruddha Ghosh; Robert J. Hijmans; Andrew Hobbs; Benson Kenduiywo; David B. Lobell. Uniting remote sensing, crop modelling and economics for agricultural risk management. Nature Reviews Earth & Environment 2021, 2, 140 -159.
AMA StyleElinor Benami, Zhenong Jin, Michael R. Carter, Aniruddha Ghosh, Robert J. Hijmans, Andrew Hobbs, Benson Kenduiywo, David B. Lobell. Uniting remote sensing, crop modelling and economics for agricultural risk management. Nature Reviews Earth & Environment. 2021; 2 (2):140-159.
Chicago/Turabian StyleElinor Benami; Zhenong Jin; Michael R. Carter; Aniruddha Ghosh; Robert J. Hijmans; Andrew Hobbs; Benson Kenduiywo; David B. Lobell. 2021. "Uniting remote sensing, crop modelling and economics for agricultural risk management." Nature Reviews Earth & Environment 2, no. 2: 140-159.
The Kenya Great Rift Valley (KGRV) region unique landscape comprises of mountainous terrain, large valley-floor lakes, and agricultural lands bordered by extensive Arid and Semi-Arid Lands (ASALs). The East Africa (EA) region has received high amounts of rainfall in the recent past as evidenced by the rising lake levels in the GRV lakes. In Kenya, few studies have quantified soil loss at national scales and erosion rates information on these GRV lakes’ regional basins within the ASALs is lacking. This study used the Revised Universal Soil Loss Equation (RUSLE) model to estimate soil erosion rates between 1990 and 2015 in the Great Rift Valley region of Kenya which is approximately 84.5% ASAL. The mean erosion rates for both periods was estimated to be tolerable (6.26 t ha−1 yr−1 and 7.14 t ha−1 yr−1 in 1990 and 2015 respectively) resulting in total soil loss of 116 Mt yr−1 and 132 Mt yr−1 in 1990 and 2015 respectively. Approximately 83% and 81% of the erosive lands in KGRV fell under the low risk category (−1 yr−1) in 1990 and 2015 respectively while about 10% were classified under the top three conservation priority levels in 2015. Lake Nakuru basin had the highest erosion rate net change (4.19 t ha−1 yr−1) among the GRV lake basins with Lake Bogoria-Baringo recording annual soil loss rates >10 t ha−1 yr−1 in both years. The mountainous central parts of the KGRV with Andosol/Nitisols soils and high rainfall experienced a large change of land uses to croplands thus had highest soil loss net change (4.34 t ha−1 yr−1). In both years, forests recorded the lowest annual soil loss rates (−1 yr−1) while most of the ASAL districts presented erosion rates (−1 yr−1). Only 34% of all the protected areas were found to have erosion rates −1 yr−1 highlighting the need for effective anti-erosive measures.
George Watene; Lijun Yu; Yueping Nie; Jianfeng Zhu; Thomas Ngigi; Jean De Dieu Nambajimana; Benson Kenduiywo. Water Erosion Risk Assessment in the Kenya Great Rift Valley Region. Sustainability 2021, 13, 844 .
AMA StyleGeorge Watene, Lijun Yu, Yueping Nie, Jianfeng Zhu, Thomas Ngigi, Jean De Dieu Nambajimana, Benson Kenduiywo. Water Erosion Risk Assessment in the Kenya Great Rift Valley Region. Sustainability. 2021; 13 (2):844.
Chicago/Turabian StyleGeorge Watene; Lijun Yu; Yueping Nie; Jianfeng Zhu; Thomas Ngigi; Jean De Dieu Nambajimana; Benson Kenduiywo. 2021. "Water Erosion Risk Assessment in the Kenya Great Rift Valley Region." Sustainability 13, no. 2: 844.
Geodetic networks development begun in Kenya and Africa as a whole at the dawn of 20th century. Consequently, enormous geodetic data has been realized. In Kenya, the data was recorded in form of paper trigonometric cards, paper topographic maps, and paper cadastral map sheets and centrally archived in the ministry of lands and physical planning headquarters in Nairobi. This was to assist locate and visualize suitable survey of Kenya geodetic pillar of interest to user. However, the user still has to commute to the headquarters in order to physically acquire coordinate information of any pillar in the country. This circumstance has fabricated a framework that has triggered accumulation of millions of paper records. The effectiveness and efficiency of serving the users is greatly undermined by the manual process. Therefore, an alternative solution is necessary to alleviate dependence on an outdated manual process. As a result, this study sought to fill this gap by designing a web geoportal for management of geodetic control networks and user access which incorporates making of payments of coordinates in different systems remotely. The geoportal comprises of an integration of a database management system, a server configuration and a website with an automated data access through a payment gateway. Java scripts and python programming languages were used. The final platform has the following capabilities: spatial visualization, co-ordinates system conversion, online payment, and request and access of data remotely. We foresee that the system will aid the ministry of lands and physical planning to disseminate geodetic information to users efficiently and effectively while tracking revenue payments.
David Maina Ndirangu; Benson Kipkemboi Kenduiywo; Edward Hunja Waithaka. A WEB-BASED GIS PORTAL FOR SIMULATING GEODETIC CONTROL NETWORKS IN REPUBLIC OF KENYA. Geodesy and cartography 2020, 46, 170 -181.
AMA StyleDavid Maina Ndirangu, Benson Kipkemboi Kenduiywo, Edward Hunja Waithaka. A WEB-BASED GIS PORTAL FOR SIMULATING GEODETIC CONTROL NETWORKS IN REPUBLIC OF KENYA. Geodesy and cartography. 2020; 46 (4):170-181.
Chicago/Turabian StyleDavid Maina Ndirangu; Benson Kipkemboi Kenduiywo; Edward Hunja Waithaka. 2020. "A WEB-BASED GIS PORTAL FOR SIMULATING GEODETIC CONTROL NETWORKS IN REPUBLIC OF KENYA." Geodesy and cartography 46, no. 4: 170-181.
Maize yield estimates are useful for county food security preparedness. Techniques such as regression and simulation have been used by various studies to model and predict maize yield. This study used a feed-forward, back propagation artificial neural network with levenberg-marquardt algorithm for training. Artificial neural networks framework was chosen because its a data driven method that is relatively less widely used in county level yield prediction. Moreover, neural networks has key merits, such as require less formal statistical training, ability to detect nonlinear relationships by identifying likely interactions between variables and the availability of multiple training algorithms. We modelled historical maize yield between 2005–2016 as function of satellite derived precipitation, temperature, reference crop evapotranspiration, soil moisture and normalized difference vegetation index (NDVI) to predict maize yields at pixel level. The data were obtained with a spatial resolution of \(\approx \) 4 km and subsequently, the predictions was done at \(\approx \) 4 km pixel size. The historical reference maize yield data was divided into two sets for model training and validation. The model predicted maize yield with \(R^2\) and root mean square error of 0.76 and 0.038 MT/ha in Trans-Nzoia county and 0.86 and 0.016 MT/ha, respectively, in Nakuru county. These findings shows a promising future for applications targeting to rapidly assess county level food preparedness in Kenya because maize is a major staple food.
Joshua Irungu Mwaura; Benson Kipkemboi Kenduiywo. County level maize yield estimation using artificial neural network. Modeling Earth Systems and Environment 2020, 7, 1417 -1424.
AMA StyleJoshua Irungu Mwaura, Benson Kipkemboi Kenduiywo. County level maize yield estimation using artificial neural network. Modeling Earth Systems and Environment. 2020; 7 (3):1417-1424.
Chicago/Turabian StyleJoshua Irungu Mwaura; Benson Kipkemboi Kenduiywo. 2020. "County level maize yield estimation using artificial neural network." Modeling Earth Systems and Environment 7, no. 3: 1417-1424.
Forest fire is one of the most serious environmental problems in Kenya that influences human activities, climate change and biodiversity. The main goal of this study is to apply medium resolution sensors (Landsat 8 OLI and Sentinel 2 MSI) to produce burnt area severity maps that will include small fires (< 100 ha) in order to improve burnt area detection and mapping in Kenya. Normalized burnt area indices were generated for specified pre- and post-fire periods. The difference between pre- and post-fire Normalized Burnt Ration (NBR) was used to compute δNBR index depicting forest disturbance by fire events. Thresholded classes were derived from the computed δNBR indices to obtain burnt severity maps. The spatial and temporal agreements of the Burnt area detection dates were validated by comparing against the MODIS MCD641 500 m products and MODIS Fire Information for Resource Management System (FIRMS) 1 km daily product hot-spot acquisition dates. This approach was implemented on Google Earth Engine (GEE) platform with a simple user interface that allows users to auto-generate burnt area maps and statistics. The operational GEE application developed can be used to obtain burnt area severity maps and statistics that allow for initial accurate approximation of fire damage.
D. Ongeri; B. K. Kenduiywo. BURNT AREA DETECTION USING MEDIUM RESOLUTION SENTINEL 2 AND LANDSAT 8 SATELLITES. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2020, XLIII-B5-2, 131 -137.
AMA StyleD. Ongeri, B. K. Kenduiywo. BURNT AREA DETECTION USING MEDIUM RESOLUTION SENTINEL 2 AND LANDSAT 8 SATELLITES. The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2020; XLIII-B5-2 ():131-137.
Chicago/Turabian StyleD. Ongeri; B. K. Kenduiywo. 2020. "BURNT AREA DETECTION USING MEDIUM RESOLUTION SENTINEL 2 AND LANDSAT 8 SATELLITES." The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLIII-B5-2, no. : 131-137.
Monitoring staple crop production can support agricultural research, business such as crop insurance, and government policy. Obtaining accurate estimates through field work is very expensive, and estimating it through remote sensing is promising. We estimated county-level maize yield for the 37 maize producing countries in Kenya from 2010 to 2017 using Moderate Resolution Imaging Spectroradiometer (MODIS) data. Support Vector Regression (SVR) and Random Forest (RF) were used to fit models with observed county level maize yield as a function of vegetation indices. The following five MODIS vegetation indices were used: green normalized difference vegetation index, normalized difference vegetation index, normalized difference moisture index, gross primary production, and fraction of photosynthetically active radiation. The models were evaluated with 5-fold leave one year out cross-validation. For SVR, R2 was 0.70, the Root Mean Square Error (RMSE) was 0.50 MT/ha and Mean Absolute Percentage Error (MAPE) was 27.6%. On the other hand for RF these were 0.69, 0.51 MT/ha and 29.3% respectively. These results are promising and should be tested in specific applications to understand if they are good enough for use.
B. K. Kenduiywo; A. Ghosh; R. Hijmans; L. Ndungu. MAIZE YIELD ESTIMATION IN KENYA USING MODIS. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2020, V-3-2020, 477 -482.
AMA StyleB. K. Kenduiywo, A. Ghosh, R. Hijmans, L. Ndungu. MAIZE YIELD ESTIMATION IN KENYA USING MODIS. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2020; V-3-2020 ():477-482.
Chicago/Turabian StyleB. K. Kenduiywo; A. Ghosh; R. Hijmans; L. Ndungu. 2020. "MAIZE YIELD ESTIMATION IN KENYA USING MODIS." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences V-3-2020, no. : 477-482.
The Kenyan coast is constantly under persistent cloud cover which hinders mapping using optical images. Up-to-date land-cover information in such areas is sometimes missing from national mapping initiatives. This study uses a computed composite image based on a mean of cloud and shadow free Function of Mask masked multi-temporal Landsat 8 images acquired during long-dry season in a pilot area. We test the effectiveness of the composite to map mangrove forest using random forest (RF) and support vector machines (SVM) machine learning algorithms integrated with context from Markov random fields (MRF(s)). MRFs was chosen because it is computationally efficient hence can be scaled out nationally. The MRF frameworks are compared to pixel-based classification using threefold independent validation samples. SVM–MRFs and RF–MRFs methods have the highest overall accuracy compared to pixel-based classification. However, visual assessment of predicted land-cover using aerial photograghs established that SVM–MRFs framework corresponded well to land-cover in the study area. This framework also managed to map classes with limited ground reference data better than RF–MRFs. Generally, context in both techniques played a discriminative role especially in heterogeneous regions. Therefore, scaling out this approaches would go a long way in generating mangrove forest map inventory in persistent cloud cover regions which is useful for land-based emission estimation.
Benson Kipkemboi Kenduiywo; Felix Nzive Mutua; Thomas Gathungu Ngigi; Edward Hunja Waithaka. Mapping mangrove forest using Landsat 8 to support estimation of land-based emissions in Kenya. Modeling Earth Systems and Environment 2020, 6, 1619 -1632.
AMA StyleBenson Kipkemboi Kenduiywo, Felix Nzive Mutua, Thomas Gathungu Ngigi, Edward Hunja Waithaka. Mapping mangrove forest using Landsat 8 to support estimation of land-based emissions in Kenya. Modeling Earth Systems and Environment. 2020; 6 (3):1619-1632.
Chicago/Turabian StyleBenson Kipkemboi Kenduiywo; Felix Nzive Mutua; Thomas Gathungu Ngigi; Edward Hunja Waithaka. 2020. "Mapping mangrove forest using Landsat 8 to support estimation of land-based emissions in Kenya." Modeling Earth Systems and Environment 6, no. 3: 1619-1632.
Soil pH is an indispensable part of the soil bionetwork, but so vulnerable to the dynamics of land-use change. Understanding the spatial and temporal distribution of soil pH is thus important for sustainable land use planning and management. In this study, we developed an approach based on geographically weighted regression-kriging (GWRK) to predict the continuous variation of soil pH up to 15 cm depth. The approach is compared to multiple linear regression-kriging (MLRK) using a total of 220 soil observations and 28 candidate auxiliary data, including climatic, topographic, and remotely sensed data. Results revealed that organic matter, sand, silt, temperature, and Landsat 8 operational land imager band 7 can explain the spatial variability of soil pH. GWR-based (local) models remarkably improved the prediction accuracy of soil pH compared to the MLR-based (global) models considering the root mean square error (i.e., 0.33 vs. 0.15; 0.37 vs. 0.17, respectively) and the coefficient of multiple determination (R2) (i.e., 0.59 vs. 0.74; 0.43 vs. 0.55, respectively). In conclusion, the use of GWR-based models revealed that the correlations between soil pH and environmental covariates were not stationary in space. Forested areas tended to be very strongly to moderately acidic, while croplands were slightly acidic to neutral. The GWR-based models demonstrated their utility in improving predictive soil mapping. These findings will support spatially-targeted soil pH management for improved food security and ecosystem health.
Brian Odhiambo; Benson Kenduiywo; Kennedy Were. Spatial prediction and mapping of soil pH across a tropical afro-montane landscape. Applied Geography 2019, 114, 102129 .
AMA StyleBrian Odhiambo, Benson Kenduiywo, Kennedy Were. Spatial prediction and mapping of soil pH across a tropical afro-montane landscape. Applied Geography. 2019; 114 ():102129.
Chicago/Turabian StyleBrian Odhiambo; Benson Kenduiywo; Kennedy Were. 2019. "Spatial prediction and mapping of soil pH across a tropical afro-montane landscape." Applied Geography 114, no. : 102129.
Jenipher Achieng’ Obiero; Mercy Mwaniki; Benson Kenduiywo. Assessment of Household Access to Groundwater: A Case Study of Gilgil Constituency. Journal of Geographic Information System 2019, 11, 293 -308.
AMA StyleJenipher Achieng’ Obiero, Mercy Mwaniki, Benson Kenduiywo. Assessment of Household Access to Groundwater: A Case Study of Gilgil Constituency. Journal of Geographic Information System. 2019; 11 (03):293-308.
Chicago/Turabian StyleJenipher Achieng’ Obiero; Mercy Mwaniki; Benson Kenduiywo. 2019. "Assessment of Household Access to Groundwater: A Case Study of Gilgil Constituency." Journal of Geographic Information System 11, no. 03: 293-308.
Water scarcity is currently still a global challenge despite the fact that water sustains life on earth. An understanding of domestic water demand is therefore vital for effective water management. In order to understand and predict future water demand, appropriate mathematical models are needed. The present work used Geographic Information Systems (GIS) based regression models; Geographically weighted regression (GWR) and Ordinary Least Square (OLS) to model domestic water demand in Athi river town. We identified a total of 7 water determinant factors in our study area. From these factors, 4 most significant ones (household size, household income, meter connections and household rooms) were identified using OLS. Further, GWR technique was used to investigate any intrinsic relationship between the factors and water demand occurrence. GWR coefficients values computed were mapped to exhibit the relationship and strength of each explanatory variable to water demand. By comparing OLS and GWR models with both AIC value and R2 value, the results demonstrated GWR model as capable of projecting water demand compared to OLS model. The GWR model was therefore adopted to predict water demand in the year 2022. It revealed domestic water demand in 2017 was estimated at 721,899 m3 compared to 880,769 m3 in 2022, explaining an increase of about 22%. Generally, the results of this study can be used by water resource planners and managers to effectively manage existing water resources and as baseline information for planning a cost-effective and reliable water supply sources to the residents of a town.
Winfred Mbinya Manetu; Felix Mutua; Benson Kenduiywo. Spatial Modelling of Current and Future Piped Domestic Water Demand in Athi River Town, Kenya. Journal of Geographic Information System 2019, 11, 196 -211.
AMA StyleWinfred Mbinya Manetu, Felix Mutua, Benson Kenduiywo. Spatial Modelling of Current and Future Piped Domestic Water Demand in Athi River Town, Kenya. Journal of Geographic Information System. 2019; 11 (02):196-211.
Chicago/Turabian StyleWinfred Mbinya Manetu; Felix Mutua; Benson Kenduiywo. 2019. "Spatial Modelling of Current and Future Piped Domestic Water Demand in Athi River Town, Kenya." Journal of Geographic Information System 11, no. 02: 196-211.
High food demand has led stakeholders to regularly monitor agricultural production to ensure food security and a balanced ecosystem. Agricultural areas undergo rapid changes throughout a growing season due to phenology. Crop mapping initiatives therefore require efficient and effective information gathering techniques. Remote sensing, specifically radar, offers an effective land-cover mapping platform compared to ground surveying methods. Radar is sensitive to crop physical structure and biomass/vegetation water content, i.e. dielectric property. We adopt and test the potential of the recent Sentinel 1 images for multitemporal crop classification due to its short revisit period and sufficient spatial resolution. The temporal resolution guarantees the highest temporal density of images that captures crop dynamics. However, this presents dimensionality problems in classification algorithms. Therefore, we chose dynamic conditional random fields (DCRFs) and tested their robustness in high-dimensional images constrained to few training data. DCRFs are designed to incorporate spatio-temporal phenological information inherent in images during crop classification. We compare the approach to single epoch classification. Our findings indicate that DCRFs improved crop mapping accuracy in all epochs. Nonetheless, most stakeholders require seasonal crop-type statistics. Hence, we use an ensemble classifier to produce an optimal map from posterior class probabilities estimated from the sequence of images. The ensemble outperforms the conventional approach of merging multitemporal images as composite bands for classification using Maximum Likelihood Classifier (MLC-stack) and mono-temporal conditional random fields. It still retains high accuracy compared to MLC-stack when subjected to high-dimensional images with fewer training data.
Benson Kipkemboi Kenduiywo; Damian Bargiel; Uwe Soergel. Crop-type mapping from a sequence of Sentinel 1 images. International Journal of Remote Sensing 2018, 39, 6383 -6404.
AMA StyleBenson Kipkemboi Kenduiywo, Damian Bargiel, Uwe Soergel. Crop-type mapping from a sequence of Sentinel 1 images. International Journal of Remote Sensing. 2018; 39 (19):6383-6404.
Chicago/Turabian StyleBenson Kipkemboi Kenduiywo; Damian Bargiel; Uwe Soergel. 2018. "Crop-type mapping from a sequence of Sentinel 1 images." International Journal of Remote Sensing 39, no. 19: 6383-6404.
The rising food demand requires regular agriculture land-cover updates to support food security initiatives. Agricultural areas undergo dynamic changes throughout the year, which manifest varying radar backscatter due to crop phenology. Certain crops can show similar backscatter if their phenology intersects, but vary later when their phenology differs. Hence, classification techniques based on single-date remote sensing images may not offer optimal results for crops with similar phenology. Moreover, methods that stack images within a cropping season as composite bands for classification limit discrimination to one feature space vector, which can suffer from overlapping classes. Nonetheless, phenology can aid classification of crops, because their backscatter varies with time. This paper fills this gap by introducing a crop sequence-based ensemble classification method where expert knowledge and TerraSAR-X multitemporal image-based phenological information are explored. We designed first-order and higher order dynamic conditional random fields (DCRFs) including an ensemble technique. The DCRF models have a duplicated structure of temporally connected CRFs, which encode image-based phenology and expert-based phenology knowledge during classification. On the other hand, our ensemble generates an optimal map based on class posterior probabilities estimated by DCRFs. These techniques improved crop delineation at each epoch, with higher order DCRFs (HDCRFs) giving the best accuracy. The ensemble method was evaluated against the conventional technique of stacking multitemporal images as composite bands for classification using maximum likelihood classifier (MLC) and CRFs. It surpassed MLC and CRFs based on class posterior probabilities estimated by both first-order DCRFs and HDCRFs.
Benson Kipkemboi Kenduiywo; Damian Bargiel; Uwe Soergel. Higher Order Dynamic Conditional Random Fields Ensemble for Crop Type Classification in Radar Images. IEEE Transactions on Geoscience and Remote Sensing 2017, 55, 4638 -4654.
AMA StyleBenson Kipkemboi Kenduiywo, Damian Bargiel, Uwe Soergel. Higher Order Dynamic Conditional Random Fields Ensemble for Crop Type Classification in Radar Images. IEEE Transactions on Geoscience and Remote Sensing. 2017; 55 (8):4638-4654.
Chicago/Turabian StyleBenson Kipkemboi Kenduiywo; Damian Bargiel; Uwe Soergel. 2017. "Higher Order Dynamic Conditional Random Fields Ensemble for Crop Type Classification in Radar Images." IEEE Transactions on Geoscience and Remote Sensing 55, no. 8: 4638-4654.
Trachoma is a neglected tropical disease and leading infectious cause of blindness, In Kenya it accounts for 19% of blindness. Past research on associated risk factors in Kenya have relied on traditional impact survey data only however non uniform distribution of prevalence in suspected endemic areas despite similar interventions measures calls for the need to include environmental and climatic potential risk factors in modeling trachoma transmission. Our study therefore aims at determining the prevalence of trachoma and its associated risks factors by use of spatial regression models in variable selection, estimation and prediction compared to conventional regression models. Through use of data from trachoma surveys and remotely sensed environmental and climatic data, spatial and non-spatial regression models were implemented. Regression results were then utilized in spatial interpolation using kriging and geographically weighted regression. Rainfall, presence of flies in children’s face, dirty faces of children and aridity were found out to be the significant variables that contributes towards trachoma transmission. Spatial lag model had the least value of akaike information criterion of 385.08 hence performed relatively better compared to the rest of the regressions models. In estimation of prevalence in places where data was not collected, multivariate regression kriging did slightly better than the geographically weighted regression. The study shows that Spatial regression models performs better compared to conventional regression models both in variable selection and in spatial prediction of trachoma prevalence. Among the spatial regressions the significant variables as obtained were similar though spatial lag performed relatively better compared to other regression models in variable selection based on AIC value and R -squared. There was minimal variation between the two spatial interpolation methods.
Pius Kipngetich Kirui; Benson Kipkemboi Kenduiywo; Edward Hunja Waithaka. Comparison of Spatial and Conventional Regression Models in Determination of Trachoma Prevalence and Associated Risk Factors. Geoinformatics & Geostatistics: An Overview 2017, 5, 1 .
AMA StylePius Kipngetich Kirui, Benson Kipkemboi Kenduiywo, Edward Hunja Waithaka. Comparison of Spatial and Conventional Regression Models in Determination of Trachoma Prevalence and Associated Risk Factors. Geoinformatics & Geostatistics: An Overview. 2017; 5 (4):1.
Chicago/Turabian StylePius Kipngetich Kirui; Benson Kipkemboi Kenduiywo; Edward Hunja Waithaka. 2017. "Comparison of Spatial and Conventional Regression Models in Determination of Trachoma Prevalence and Associated Risk Factors." Geoinformatics & Geostatistics: An Overview 5, no. 4: 1.
We propose a novel time series analysis based on persistent scatterer interferometry (PSI) to detect spatial big changes (3D) such as construction along with their occurrence times (1D). PSI detects and analyses persistent scatterer (PS) points, which are characterized by strong and coherent signals throughout time-series SAR images and usually form building-shaped patterns in urban areas. Hence, potential PS points that disappear or emerge at a specific date because of big changes are discarded. We define such points as big change (BC) points. In our approach, pixels with high temporal coherences are first detected as PS points by a standard PSI processing. We introduce change index sequence for each pixel, which are computed from its temporal coherences in different image subsets defined by time-series break dates, to quantify its probabilities of being BC points at different dates. The change indices of the pixels are used to design an automatic thresholding method to extract BC points. Afterwards, the disappearing or emerging date of each BC point is detected from the break dates based on temporal variation in its change index sequence. The simulation test proves the overall, producer's and user's accuracies better than 99%. In the real data test, the patterns of the disappearing and emerging buildings are successfully recognized in Berlin, Germany along with the occurrence dates.
Chia-Hsiang Yang; Benson Kipkemboi Kenduiywo; Uwe Soergel. 4D change detection based on persistent scatterer interferometry. 2016 9th IAPR Workshop on Pattern Recogniton in Remote Sensing (PRRS) 2016, 1 -6.
AMA StyleChia-Hsiang Yang, Benson Kipkemboi Kenduiywo, Uwe Soergel. 4D change detection based on persistent scatterer interferometry. 2016 9th IAPR Workshop on Pattern Recogniton in Remote Sensing (PRRS). 2016; ():1-6.
Chicago/Turabian StyleChia-Hsiang Yang; Benson Kipkemboi Kenduiywo; Uwe Soergel. 2016. "4D change detection based on persistent scatterer interferometry." 2016 9th IAPR Workshop on Pattern Recogniton in Remote Sensing (PRRS) , no. : 1-6.
Crop phenology is dynamic as it changes with times of the year. Such biophysical processes also look spectrally different to remote sensing satellites. Some crops may depict similar spectral properties if their phenology coincide, but differ later when their phenology diverge. Thus, conventional approaches that select only images from phenological stages where crops are distinguishable for classification, have low discrimination. In contrast, stacking images within a cropping season limits discrimination to a single feature space that can suffer from overlapping classes. Since crop backscatter varies with time, it can aid discrimination. Therefore, our main objective is to develop a crop sequence classification method using multitemporal TerraSAR-X images. We adopt first order markov assumption in undirected temporal graph sequence. This property is exploited to implement Dynamic Conditional Random Fields (DCRFs). Our DCRFs model has a repeated structure of temporally connected Conditional Random Fields (CRFs). Each node in the sequence is connected to its predecessor via conditional probability matrix. The matrix is computed using posterior class probabilities from association potential. This way, there is a mutual temporal exchange of phenological information observed in TerraSAR-X images. When compared to independent epoch classification, the designed DCRF model improved crop discrimination at each epoch in the sequence. However, government, insurers, agricultural market traders and other stakeholders are interested in the quantity of a certain crop in a season. Therefore, we further develop a DCRF ensemble classifier. The ensemble produces an optimal crop map by maximizing over posterior class probabilities selected from the sequence based on maximum F1-score and weighted by correctness. Our ensemble technique is compared to standard approach of stacking all images as bands for classification using Maximum Likelihood Classifier (MLC) and standard CRFs. It outperforms MLC and CRFs by 7.70% and 6.42% in overall accuracy, respectively.
Benson Kenduiywo; D. Bargiel; U. Soergel. CROP TYPE MAPPING FROM A SEQUENCE OF TERRASAR-X IMAGES WITH DYNAMIC CONDITIONAL RANDOM FIELDS. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2016, III-7, 59 -66.
AMA StyleBenson Kenduiywo, D. Bargiel, U. Soergel. CROP TYPE MAPPING FROM A SEQUENCE OF TERRASAR-X IMAGES WITH DYNAMIC CONDITIONAL RANDOM FIELDS. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2016; III-7 ():59-66.
Chicago/Turabian StyleBenson Kenduiywo; D. Bargiel; U. Soergel. 2016. "CROP TYPE MAPPING FROM A SEQUENCE OF TERRASAR-X IMAGES WITH DYNAMIC CONDITIONAL RANDOM FIELDS." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences III-7, no. : 59-66.
Persistent Scatterer Interferometry (PSI) is a technique to detect a network of extracted persistent scatterer (PS) points which feature temporal phase stability and strong radar signal throughout time-series of SAR images. The small surface deformations on such PS points are estimated. PSI particularly works well in monitoring human settlements because regular substructures of man-made objects give rise to large number of PS points. If such structures and/or substructures substantially alter or even vanish due to big change like construction, their PS points are discarded without additional explorations during standard PSI procedure. Such rejected points are called big change (BC) points. On the other hand, incoherent change detection (ICD) relies on local comparison of multi-temporal images (e.g. image difference, image ratio) to highlight scene modifications of larger size rather than detail level. However, image noise inevitably degrades ICD accuracy. We propose a change detection approach based on PSI to synergize benefits of PSI and ICD. PS points are extracted by PSI procedure. A local change index is introduced to quantify probability of a big change for each point. We propose an automatic thresholding method adopting change index to extract BC points along with a clue of the period they emerge. In the end, PS ad BC points are integrated into a change detection image. Our method is tested at a site located around north of Berlin main station where steady, demolished, and erected building substructures are successfully detected. The results are consistent with ground truth derived from time-series of aerial images provided by Google Earth. In addition, we apply our technique for traffic infrastructure, business district, and sports playground monitoring.
C. H. Yang; B. K. Kenduiywo; U. Soergel. CHANGE DETECTION BASED ON PERSISTENT SCATTERER INTERFEROMETRY – A NEW METHOD OF MONITORING BUILDING CHANGES. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2016, III-7, 243 -250.
AMA StyleC. H. Yang, B. K. Kenduiywo, U. Soergel. CHANGE DETECTION BASED ON PERSISTENT SCATTERER INTERFEROMETRY – A NEW METHOD OF MONITORING BUILDING CHANGES. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2016; III-7 ():243-250.
Chicago/Turabian StyleC. H. Yang; B. K. Kenduiywo; U. Soergel. 2016. "CHANGE DETECTION BASED ON PERSISTENT SCATTERER INTERFEROMETRY – A NEW METHOD OF MONITORING BUILDING CHANGES." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences III-7, no. : 243-250.
The rapid increase in population in the world has propelled pressure on arable land. Consequently, the food basket has continuously declined while global demand for food has grown twofold. There is need to monitor and update agriculture land-cover to support food security measures. This study develops a spatial-temporal approach using conditional random fields (CRF) to classify co-registered images acquired in two epochs. We adopt random forest (RF) as CRF association potential and introduce a temporal potential for mutual crop phenology information exchange between spatially corresponding sites in two epochs. An important component of temporal potential is a transitional matrix that bears intra- and inter-class changes between considered epochs. Conventionally, one matrix has been used in the entire image thereby enforcing stationary transition probabilities in all sites. We introduce a site dependent transition matrix to incorporate phenology information from images. In our study, images are acquired within a vegetation season, thus perceived spectral changes are due to crop phenology. To exploit this phenomena, we develop a novel approach to determine site-wise transition matrix using conditional probabilities computed from two corresponding temporal sites. Conditional probability determines transitions between classes in different epochs and thus we used it to propagate crop phenology information. Classification results show that our approach improved crop discrimination in all epochs compared to state-of-the-art mono-temporal approaches (RF and CRF monotemporal) and existing multi-temporal markov random fields approach by Liu et al. (2008).
B. K. Kenduiywoa; D. Bargiel; U. Soergel. SPATIAL-TEMPORAL CONDITIONAL RANDOM FIELDS CROP CLASSIFICATION FROM TERRASAR-X IMAGES. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2015, II-3/W4, 79 -86.
AMA StyleB. K. Kenduiywoa, D. Bargiel, U. Soergel. SPATIAL-TEMPORAL CONDITIONAL RANDOM FIELDS CROP CLASSIFICATION FROM TERRASAR-X IMAGES. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2015; II-3/W4 ():79-86.
Chicago/Turabian StyleB. K. Kenduiywoa; D. Bargiel; U. Soergel. 2015. "SPATIAL-TEMPORAL CONDITIONAL RANDOM FIELDS CROP CLASSIFICATION FROM TERRASAR-X IMAGES." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences II-3/W4, no. : 79-86.
Classifying built-up areas from satellite images is a challenging task due to spatial and spectral heterogeneity of the classes. In this study, a contextual classification method based on conditional random fields (CRFs) has been used. Spatial and spectral information from blocks of pixels were employed to identify built-up areas. The CRF association potential was based on support vector machines (SVMs), whereas the CRF interaction potential included a data-dependent term using the inverse of the transformed Euclidean distance. In this way, accuracy was stable for a varying smoothness parameter, while preserving class boundaries and aggregating similar labels, and a discontinuity adaptive model was obtained and conditioned on data evidence. The classification was applied on satellite towns around the city of Nairobi, Kenya. The accuracy exceeded that of Markov random fields, SVM, and maximum likelihood classification by 1.13%, 2.22%, and 8.23%, respectively. The CRF method had the lowest fraction of false positives. The study concluded that CRFs can be used to better detect built-up areas. In this way, it provides accurate timely spatial information to urban planners and other professionals.
Benson Kipkemboi Kenduiywo; Valentyn A. Tolpekin; Alfred Stein. Detection of built-up area in optical and synthetic aperture radar images using conditional random fields. Journal of Applied Remote Sensing 2014, 8, 083672 -083672.
AMA StyleBenson Kipkemboi Kenduiywo, Valentyn A. Tolpekin, Alfred Stein. Detection of built-up area in optical and synthetic aperture radar images using conditional random fields. Journal of Applied Remote Sensing. 2014; 8 (1):083672-083672.
Chicago/Turabian StyleBenson Kipkemboi Kenduiywo; Valentyn A. Tolpekin; Alfred Stein. 2014. "Detection of built-up area in optical and synthetic aperture radar images using conditional random fields." Journal of Applied Remote Sensing 8, no. 1: 083672-083672.
Benson Kipkemboi Kenduiywo; Valentyn A. Tolpekin; Alfred Stein. Detection of built-up area expansion in ASTER and SAR images using conditional random fields. SPIE Remote Sensing 2012, 85370N -85370N-19.
AMA StyleBenson Kipkemboi Kenduiywo, Valentyn A. Tolpekin, Alfred Stein. Detection of built-up area expansion in ASTER and SAR images using conditional random fields. SPIE Remote Sensing. 2012; ():85370N-85370N-19.
Chicago/Turabian StyleBenson Kipkemboi Kenduiywo; Valentyn A. Tolpekin; Alfred Stein. 2012. "Detection of built-up area expansion in ASTER and SAR images using conditional random fields." SPIE Remote Sensing , no. : 85370N-85370N-19.