@article{tiwari_thorp_tulbure_gray_kamruzzaman_krupnik_sankarasubramanian_ardon_2024, title={Advancing food security: Rice yield estimation framework using time-series satellite data & machine learning}, volume={19}, ISSN={["1932-6203"]}, DOI={10.1371/journal.pone.0309982}, abstractNote={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.}, number={12}, journal={PLOS ONE}, author={Tiwari, Varun and Thorp, Kelly and Tulbure, Mirela G. and Gray, Joshua and Kamruzzaman, Mohammad and Krupnik, Timothy J. and Sankarasubramanian, A. and Ardon, Marcelo}, year={2024}, month={Dec} }
 @article{tiwari_tulbure_caineta_gaines_perin_kamal_krupnik_aziz_islam_2024, title={Automated in-season rice crop mapping using Sentinel time-series data and Google Earth Engine: A case study in climate-risk prone Bangladesh}, volume={351}, ISSN={["1095-8630"]}, url={https://doi.org/10.1016/j.jenvman.2023.119615}, DOI={10.1016/j.jenvman.2023.119615}, abstractNote={High-resolution mapping of rice fields is crucial for understanding and managing rice cultivation in countries like Bangladesh, particularly in the face of climate change. Rice is a vital crop, cultivated in small scale farms that contributes significantly to the economy and food security in Bangladesh. Accurate mapping can facilitate improved rice production, the development of sustainable agricultural management policies, and formulation of strategies for adapting to climatic risks. To address the need for timely and accurate rice mapping, we developed a framework specifically designed for the diverse environmental conditions in Bangladesh. We utilized Sentinel-1 and Sentinel-2 time-series data to identify transplantation and peak seasons and employed the multi-Otsu automatic thresholding approach to map rice during the peak season (April-May). We also compared the performance of a random forest (RF) classifier with the multi-Otsu approach using two different data combinations: D1, which utilizes data from the transplantation and peak seasons (D1 RF) and D2, which utilizes data from the transplantation to the harvest seasons (D2 RF). Our results demonstrated that the multi-Otsu approach achieved an overall classification accuracy (OCA) ranging from 61.18% to 94.43% across all crop zones. The D2 RF showed the highest mean OCA (92.15%) among the fourteen crop zones, followed by D1 RF (89.47%) and multi-Otsu (85.27%). Although the multi-Otsu approach had relatively lower OCA, it proved effective in accurately mapping rice areas prior to harvest, eliminating the need for training samples that can be challenging to obtain during the growing season. In-season rice area maps generated through this framework are crucial for timely decision-making regarding adaptive management in response to climatic stresses and forecasting area-wide productivity. The scalability of our framework across space and time makes it particularly suitable for addressing field data scarcity challenges in countries like Bangladesh and offers the potential for future operationalization.}, journal={JOURNAL OF ENVIRONMENTAL MANAGEMENT}, author={Tiwari, Varun and Tulbure, Mirela G. and Caineta, Julio and Gaines, Mollie D. and Perin, Vinicius and Kamal, Mustafa and Krupnik, Timothy J. and Aziz, Md Abdullah and Islam, A. F. M. Tariqul}, year={2024}, month={Feb} }
 @article{gaines_tulbure_perin_composto_tiwari_2024, title={Projecting Surface Water Area Under Different Climate and Development Scenarios}, volume={12}, ISSN={["2328-4277"]}, url={https://doi.org/10.1029/2024EF004625}, DOI={10.1029/2024EF004625}, abstractNote={Abstract Changes in climate and land‐use/land‐cover will impact surface water dynamics throughout the 21st century and influence global surface water availability. However, most projections of surface water dynamics focus on climate drivers using local‐scale hydrological models, with few studies accounting for climate and human drivers such as land‐use/land‐cover change. We used a data‐driven, machine learning model to project seasonal surface water areas (SWAs) in the southeastern U.S. from 2006 to 2099 that combined land‐cover and climate projections under eight different development and emissions scenarios. The model was fitted with historic Landsat imagery, land‐use/land‐cover, and climate observation data (mean squared error 0.14). We assessed the change in SWA for each scenario, and we compared the surface water projections from our data‐driven model and a process‐based model. We found that the scenario with the largest forest‐dominated land cover loss and most extreme climate change had watersheds with the greatest projected increases (in the South Atlantic Gulf) and decreases (in the Lower Mississippi) in SWA. When compared to the increase or decrease in surface water projected by the process‐based model, most of the watersheds across scenarios agreed on the direction of change. Our findings highlight the importance of forest‐dominated land cover in maintaining stable surface water availability throughout the 21st century, which can inform land‐use management policies for adaptation and water‐stress mitigation as well as strategies to prepare for future flood and drought events.}, number={7}, journal={EARTHS FUTURE}, author={Gaines, Mollie D. and Tulbure, Mirela G. and Perin, Vinicius and Composto, Rebecca and Tiwari, Varun}, year={2024}, month={Jul} }