Assessing the accuracy of multi-model approaches for downscaling land surface temperature across diverse agroclimatic zones

Land surface temperature (LST) is a critical parameter for land surface and atmospheric interactions. However, the applicability of current LST estimates for field-level hydrological, agricultural, and ecological operations is challenging due to their coarse spatiotemporal resolution. In the current...

Full description

Bibliographic Details
Main Authors: Roy, Debasish, Das, Bappa, Singh, Pooja, Santra, Priyabrata, Deb, Shovik, Kumar Bhattacharya, Bimal, Govind, Ajit, Jatav, Raghuveer, Sethi, Deepak, Ghosh, Tridiv, Mukherjee, Joydeep, Kumar Sehgal, Vinay, Kumar Jha, Prakash, Goroshi, Sheshakumar, Vara Prasad, V. P., Chakraborty, Debashis
Format: Journal Article
Language:Inglés
Published: Springer Nature [academic journals on nature.com] 2025
Subjects:
Online Access:https://hdl.handle.net/10568/175174
_version_ 1855538326928359424
author Roy, Debasish
Das, Bappa
Singh, Pooja
Santra, Priyabrata
Deb, Shovik
Kumar Bhattacharya, Bimal
Govind, Ajit
Jatav, Raghuveer
Sethi, Deepak
Ghosh, Tridiv
Mukherjee, Joydeep
Kumar Sehgal, Vinay
Kumar Jha, Prakash
Goroshi, Sheshakumar
Vara Prasad, V. P.
Chakraborty, Debashis
author_browse Chakraborty, Debashis
Das, Bappa
Deb, Shovik
Ghosh, Tridiv
Goroshi, Sheshakumar
Govind, Ajit
Jatav, Raghuveer
Kumar Bhattacharya, Bimal
Kumar Jha, Prakash
Kumar Sehgal, Vinay
Mukherjee, Joydeep
Roy, Debasish
Santra, Priyabrata
Sethi, Deepak
Singh, Pooja
Vara Prasad, V. P.
author_facet Roy, Debasish
Das, Bappa
Singh, Pooja
Santra, Priyabrata
Deb, Shovik
Kumar Bhattacharya, Bimal
Govind, Ajit
Jatav, Raghuveer
Sethi, Deepak
Ghosh, Tridiv
Mukherjee, Joydeep
Kumar Sehgal, Vinay
Kumar Jha, Prakash
Goroshi, Sheshakumar
Vara Prasad, V. P.
Chakraborty, Debashis
author_sort Roy, Debasish
collection Repository of Agricultural Research Outputs (CGSpace)
description Land surface temperature (LST) is a critical parameter for land surface and atmospheric interactions. However, the applicability of current LST estimates for field-level hydrological, agricultural, and ecological operations is challenging due to their coarse spatiotemporal resolution. In the current article, we compared three different models, namely 1) Thermal Sharpening (TsHARP), 2) Thin Plate Spline (TPS), and 3) Random Forest (RF) for downscaling LST from 100 to 10 m by using high-resolution Sentinel-1,2 optical-microwave data. TsHARP, TPS, and RF are commonly used methods for improving the spatial resolution of large-scale environmental or climate data to finer scales for field-level applications. The analysis was performed at agricultural farms in the semi-arid, arid, and per-humid regions of India during the winter and summer seasons of 2020–21 and 2021–22. The calibration accuracy of the RF model was in better agreement with the coefficient of determination (R2), root mean square error (RMSE), and normalized RMSE (nRMSE) values ranging between 0.961–0.997, 0.103–0.439 K, and 0.034–0.143%, respectively, and lower values of standard errors for all three locations. Though the validation accuracy of models varied between the regions, RF and TPS consistently outperformed the TsHARP model. Further the impact of individual features on LST downscaling was analyzed using Accumulated Local Effects (ALE) plot. The study concluded that RF is an effective and adaptable strategy that can be used in various agroclimatic zones and land cover types, suggesting its broader applicability in agricultural and ecological operations. Finer resolution LST data with enhanced precision can support tailored field-level decision-making and interventions in agriculture and environmental monitoring.
format Journal Article
id CGSpace175174
institution CGIAR Consortium
language Inglés
publishDate 2025
publishDateRange 2025
publishDateSort 2025
publisher Springer Nature [academic journals on nature.com]
publisherStr Springer Nature [academic journals on nature.com]
record_format dspace
spelling CGSpace1751742026-01-14T02:15:23Z Assessing the accuracy of multi-model approaches for downscaling land surface temperature across diverse agroclimatic zones Roy, Debasish Das, Bappa Singh, Pooja Santra, Priyabrata Deb, Shovik Kumar Bhattacharya, Bimal Govind, Ajit Jatav, Raghuveer Sethi, Deepak Ghosh, Tridiv Mukherjee, Joydeep Kumar Sehgal, Vinay Kumar Jha, Prakash Goroshi, Sheshakumar Vara Prasad, V. P. Chakraborty, Debashis land surface temperature (lst) ml-based multi-parameter nonlinear regression model (rf) Land surface temperature (LST) is a critical parameter for land surface and atmospheric interactions. However, the applicability of current LST estimates for field-level hydrological, agricultural, and ecological operations is challenging due to their coarse spatiotemporal resolution. In the current article, we compared three different models, namely 1) Thermal Sharpening (TsHARP), 2) Thin Plate Spline (TPS), and 3) Random Forest (RF) for downscaling LST from 100 to 10 m by using high-resolution Sentinel-1,2 optical-microwave data. TsHARP, TPS, and RF are commonly used methods for improving the spatial resolution of large-scale environmental or climate data to finer scales for field-level applications. The analysis was performed at agricultural farms in the semi-arid, arid, and per-humid regions of India during the winter and summer seasons of 2020–21 and 2021–22. The calibration accuracy of the RF model was in better agreement with the coefficient of determination (R2), root mean square error (RMSE), and normalized RMSE (nRMSE) values ranging between 0.961–0.997, 0.103–0.439 K, and 0.034–0.143%, respectively, and lower values of standard errors for all three locations. Though the validation accuracy of models varied between the regions, RF and TPS consistently outperformed the TsHARP model. Further the impact of individual features on LST downscaling was analyzed using Accumulated Local Effects (ALE) plot. The study concluded that RF is an effective and adaptable strategy that can be used in various agroclimatic zones and land cover types, suggesting its broader applicability in agricultural and ecological operations. Finer resolution LST data with enhanced precision can support tailored field-level decision-making and interventions in agriculture and environmental monitoring. 2025-03-28 2025-06-18T18:30:44Z 2025-06-18T18:30:44Z Journal Article https://hdl.handle.net/10568/175174 en Open Access application/pdf Springer Nature [academic journals on nature.com] Debasish Roy, Bappa Das, Pooja Singh, Priyabrata Santra, Shovik Deb, Bimal Kumar Bhattacharya, Ajit Govind, Raghuveer Jatav, Deepak Sethi, Tridiv Ghosh, Joydeep Mukherjee, Vinay Kumar Sehgal, Prakash Kumar Jha, Sheshakumar Goroshi, V. P. Vara Prasad, Debashis Chakraborty. (28/3/2025). Assessing the accuracy of multi-model approaches for downscaling land surface temperature across diverse agroclimatic zones. Scientific Reports, 15.
spellingShingle land surface temperature (lst)
ml-based multi-parameter nonlinear regression model (rf)
Roy, Debasish
Das, Bappa
Singh, Pooja
Santra, Priyabrata
Deb, Shovik
Kumar Bhattacharya, Bimal
Govind, Ajit
Jatav, Raghuveer
Sethi, Deepak
Ghosh, Tridiv
Mukherjee, Joydeep
Kumar Sehgal, Vinay
Kumar Jha, Prakash
Goroshi, Sheshakumar
Vara Prasad, V. P.
Chakraborty, Debashis
Assessing the accuracy of multi-model approaches for downscaling land surface temperature across diverse agroclimatic zones
title Assessing the accuracy of multi-model approaches for downscaling land surface temperature across diverse agroclimatic zones
title_full Assessing the accuracy of multi-model approaches for downscaling land surface temperature across diverse agroclimatic zones
title_fullStr Assessing the accuracy of multi-model approaches for downscaling land surface temperature across diverse agroclimatic zones
title_full_unstemmed Assessing the accuracy of multi-model approaches for downscaling land surface temperature across diverse agroclimatic zones
title_short Assessing the accuracy of multi-model approaches for downscaling land surface temperature across diverse agroclimatic zones
title_sort assessing the accuracy of multi model approaches for downscaling land surface temperature across diverse agroclimatic zones
topic land surface temperature (lst)
ml-based multi-parameter nonlinear regression model (rf)
url https://hdl.handle.net/10568/175174
work_keys_str_mv AT roydebasish assessingtheaccuracyofmultimodelapproachesfordownscalinglandsurfacetemperatureacrossdiverseagroclimaticzones
AT dasbappa assessingtheaccuracyofmultimodelapproachesfordownscalinglandsurfacetemperatureacrossdiverseagroclimaticzones
AT singhpooja assessingtheaccuracyofmultimodelapproachesfordownscalinglandsurfacetemperatureacrossdiverseagroclimaticzones
AT santrapriyabrata assessingtheaccuracyofmultimodelapproachesfordownscalinglandsurfacetemperatureacrossdiverseagroclimaticzones
AT debshovik assessingtheaccuracyofmultimodelapproachesfordownscalinglandsurfacetemperatureacrossdiverseagroclimaticzones
AT kumarbhattacharyabimal assessingtheaccuracyofmultimodelapproachesfordownscalinglandsurfacetemperatureacrossdiverseagroclimaticzones
AT govindajit assessingtheaccuracyofmultimodelapproachesfordownscalinglandsurfacetemperatureacrossdiverseagroclimaticzones
AT jatavraghuveer assessingtheaccuracyofmultimodelapproachesfordownscalinglandsurfacetemperatureacrossdiverseagroclimaticzones
AT sethideepak assessingtheaccuracyofmultimodelapproachesfordownscalinglandsurfacetemperatureacrossdiverseagroclimaticzones
AT ghoshtridiv assessingtheaccuracyofmultimodelapproachesfordownscalinglandsurfacetemperatureacrossdiverseagroclimaticzones
AT mukherjeejoydeep assessingtheaccuracyofmultimodelapproachesfordownscalinglandsurfacetemperatureacrossdiverseagroclimaticzones
AT kumarsehgalvinay assessingtheaccuracyofmultimodelapproachesfordownscalinglandsurfacetemperatureacrossdiverseagroclimaticzones
AT kumarjhaprakash assessingtheaccuracyofmultimodelapproachesfordownscalinglandsurfacetemperatureacrossdiverseagroclimaticzones
AT goroshisheshakumar assessingtheaccuracyofmultimodelapproachesfordownscalinglandsurfacetemperatureacrossdiverseagroclimaticzones
AT varaprasadvp assessingtheaccuracyofmultimodelapproachesfordownscalinglandsurfacetemperatureacrossdiverseagroclimaticzones
AT chakrabortydebashis assessingtheaccuracyofmultimodelapproachesfordownscalinglandsurfacetemperatureacrossdiverseagroclimaticzones