Advancing food security: rice yield estimation framework using time-series satellite data & machine learning

Timely and accurately estimating rice yields is crucial for supporting food security management, agricultural policy development, and climate change adaptation in rice-producing countries such as Bangladesh. To address this need, this study introduced a workflow to enable timely and precise rice yie...

Full description

Bibliographic Details
Main Authors: Tiwari, Varun, Thorp, Kelly, Tulbure, Mirela G., Gray, Joshua, Kamruzzaman, Mohammad, Krupnik, Timothy J., Sankarasubramanian, A., Ardon, Marcelo
Format: Journal Article
Language:Inglés
Published: 2024
Subjects:
Online Access:https://hdl.handle.net/10568/169956
_version_ 1855526288654073856
author Tiwari, Varun
Thorp, Kelly
Tulbure, Mirela G.
Gray, Joshua
Kamruzzaman, Mohammad
Krupnik, Timothy J.
Sankarasubramanian, A.
Ardon, Marcelo
author_browse Ardon, Marcelo
Gray, Joshua
Kamruzzaman, Mohammad
Krupnik, Timothy J.
Sankarasubramanian, A.
Thorp, Kelly
Tiwari, Varun
Tulbure, Mirela G.
author_facet Tiwari, Varun
Thorp, Kelly
Tulbure, Mirela G.
Gray, Joshua
Kamruzzaman, Mohammad
Krupnik, Timothy J.
Sankarasubramanian, A.
Ardon, Marcelo
author_sort Tiwari, Varun
collection Repository of Agricultural Research Outputs (CGSpace)
description Timely and accurately estimating rice yields is crucial for supporting food security management, agricultural policy development, and climate change adaptation in rice-producing countries such as Bangladesh. To address this need, this study introduced a workflow to enable timely and precise rice yield estimation at a sub-district scale (1,000-meter spatial resolution). However, a significant gap exists in the application of remote sensing methods for government-reported rice yield estimation for food security management at high spatial resolution. Current methods are limited to specific regions and primarily used for research, lacking integration into national reporting systems. Additionally, there is no consistent yearly boro rice yield map at a sub-district scale, hindering localized agricultural decision-making. This workflow leveraged MODIS and annual district-level yield data to train a random forest model for estimating boro rice yields at a 1,000-meter resolution from 2002 to 2021. The results revealed a mean percentage root mean square error (RMSE) of 8.07% and 12.96% when validation was conducted using reported district yields and crop-cut yield data, respectively. Additionally, the estimated yield of boro rice varies with an uncertainty range between 0.40 and 0.45 tons per hectare across Bangladesh. Furthermore, a trend analysis was performed on the estimated boro rice yield data from 2002 to 2021 using the modified Mann-Kendall trend test with a 95% confidence interval (p < 0.05). In Bangladesh, 23% of the rice area exhibits an increasing trend in boro rice yield, 0.11% shows a decreasing trend, and 76.51% of the area demonstrates no trend in rice yield. Given that this is the first attempt to estimate boro rice yield at 1,000-meter spatial resolution over two decades in Bangladesh, the estimated mid-season boro rice yield estimates are scalable across space and time, offering significant potential for strengthening food security management in Bangladesh. Furthermore, the proposed workflow can be easily applied to estimate rice yields in other regions worldwide.
format Journal Article
id CGSpace169956
institution CGIAR Consortium
language Inglés
publishDate 2024
publishDateRange 2024
publishDateSort 2024
record_format dspace
spelling CGSpace1699562025-10-26T12:51:48Z Advancing food security: rice yield estimation framework using time-series satellite data & machine learning Tiwari, Varun Thorp, Kelly Tulbure, Mirela G. Gray, Joshua Kamruzzaman, Mohammad Krupnik, Timothy J. Sankarasubramanian, A. Ardon, Marcelo food security rice crop yield machine learning climate change adaptation satellites data Timely and accurately estimating rice yields is crucial for supporting food security management, agricultural policy development, and climate change adaptation in rice-producing countries such as Bangladesh. To address this need, this study introduced a workflow to enable timely and precise rice yield estimation at a sub-district scale (1,000-meter spatial resolution). However, a significant gap exists in the application of remote sensing methods for government-reported rice yield estimation for food security management at high spatial resolution. Current methods are limited to specific regions and primarily used for research, lacking integration into national reporting systems. Additionally, there is no consistent yearly boro rice yield map at a sub-district scale, hindering localized agricultural decision-making. This workflow leveraged MODIS and annual district-level yield data to train a random forest model for estimating boro rice yields at a 1,000-meter resolution from 2002 to 2021. The results revealed a mean percentage root mean square error (RMSE) of 8.07% and 12.96% when validation was conducted using reported district yields and crop-cut yield data, respectively. Additionally, the estimated yield of boro rice varies with an uncertainty range between 0.40 and 0.45 tons per hectare across Bangladesh. Furthermore, a trend analysis was performed on the estimated boro rice yield data from 2002 to 2021 using the modified Mann-Kendall trend test with a 95% confidence interval (p < 0.05). In Bangladesh, 23% of the rice area exhibits an increasing trend in boro rice yield, 0.11% shows a decreasing trend, and 76.51% of the area demonstrates no trend in rice yield. Given that this is the first attempt to estimate boro rice yield at 1,000-meter spatial resolution over two decades in Bangladesh, the estimated mid-season boro rice yield estimates are scalable across space and time, offering significant potential for strengthening food security management in Bangladesh. Furthermore, the proposed workflow can be easily applied to estimate rice yields in other regions worldwide. 2024-12-12 2025-01-26T02:47:28Z 2025-01-26T02:47:28Z Journal Article https://hdl.handle.net/10568/169956 en Open Access application/pdf Tiwari, V., Thorp, K., Tulbure, M. G., Gray, J., Kamruzzaman, M., Krupnik, T. J., Sankarasubramanian, A., & Ardon, M. (2024). Advancing food security: rice yield estimation framework using time-series satellite data & machine learning. PLoS ONE, 19(12), e0309982. https://doi.org/10.1371/journal.pone.0309982
spellingShingle food security
rice
crop yield
machine learning
climate change adaptation
satellites
data
Tiwari, Varun
Thorp, Kelly
Tulbure, Mirela G.
Gray, Joshua
Kamruzzaman, Mohammad
Krupnik, Timothy J.
Sankarasubramanian, A.
Ardon, Marcelo
Advancing food security: rice yield estimation framework using time-series satellite data & machine learning
title Advancing food security: rice yield estimation framework using time-series satellite data & machine learning
title_full Advancing food security: rice yield estimation framework using time-series satellite data & machine learning
title_fullStr Advancing food security: rice yield estimation framework using time-series satellite data & machine learning
title_full_unstemmed Advancing food security: rice yield estimation framework using time-series satellite data & machine learning
title_short Advancing food security: rice yield estimation framework using time-series satellite data & machine learning
title_sort advancing food security rice yield estimation framework using time series satellite data machine learning
topic food security
rice
crop yield
machine learning
climate change adaptation
satellites
data
url https://hdl.handle.net/10568/169956
work_keys_str_mv AT tiwarivarun advancingfoodsecurityriceyieldestimationframeworkusingtimeseriessatellitedatamachinelearning
AT thorpkelly advancingfoodsecurityriceyieldestimationframeworkusingtimeseriessatellitedatamachinelearning
AT tulburemirelag advancingfoodsecurityriceyieldestimationframeworkusingtimeseriessatellitedatamachinelearning
AT grayjoshua advancingfoodsecurityriceyieldestimationframeworkusingtimeseriessatellitedatamachinelearning
AT kamruzzamanmohammad advancingfoodsecurityriceyieldestimationframeworkusingtimeseriessatellitedatamachinelearning
AT krupniktimothyj advancingfoodsecurityriceyieldestimationframeworkusingtimeseriessatellitedatamachinelearning
AT sankarasubramaniana advancingfoodsecurityriceyieldestimationframeworkusingtimeseriessatellitedatamachinelearning
AT ardonmarcelo advancingfoodsecurityriceyieldestimationframeworkusingtimeseriessatellitedatamachinelearning