The mixed effects of recent cover crop adoption on U.S. cropland productivity DOI Creative Commons
David B. Lobell, Stefania Di Tommaso, Qu Zhou

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 25, 2024

Abstract Farmers in the United States have rapidly expanded use of cover crops (CC), with national CC area nearly doubling since 2012. Despite many benefits that motivate public subsidies, questions remain about potential downsides. Using satellite observations from over 100,000 fields, half which recently adopted CC, we demonstrate led to: (i) declines average yields for corn and soybean, by ~3% ~2%, respectively; (ii) delays sowing (4 days) soybean (3 days); (iii) reduced damages wet spring 2019, fields only as likely to experience prevented planting non-CC fields. appears reduce important aspects farmer risk conditions but increase them dry conditions. Timely cash crop deserves emphasis moving forward, show eliminating would yield penalties roughly 50% 90% soybean.

Language: Английский

Dynamic Maize True Leaf Area Index Retrieval with KGCNN and TL and Integrated 3D Radiative Transfer Modeling for Crop Phenotyping DOI Creative Commons
Dan Zhao, Guijun Yang, Tongyu Xu

et al.

Plant Phenomics, Journal Year: 2025, Volume and Issue: unknown, P. 100004 - 100004

Published: Feb. 1, 2025

Language: Английский

Citations

1
Mapping and Analyzing Winter Wheat Yields in the Huang-Huai-Hai Plain: A Climate-Independent Perspective DOI Creative Commons
Yachao Zhao, Xin Du, Qiangzi Li

et al.

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(8), P. 1409 - 1409

Published: April 16, 2025

Accurate diagnostics of crop yields are essential for climate-resilient agricultural planning; however, conventional datasets often conflate environmental covariates during model training. Here, we present HHHWheatYield1km, a 1 km resolution winter wheat yield dataset China’s Huang-Huai-Hai Plain spanning 2000–2019. By integrating climate-independent multi-source remote sensing metrics with Random Forest model, calibrated against municipal statistical yearbooks, the exhibits strong agreement county-level records (R = 0.90, RMSE 542.47 kg/ha, MRE 9.09%), ensuring independence from climatic influences robust driver analysis. Using Geodetector, reveal pronounced spatial heterogeneity in climate–yield interactions, highlighting distinct regional disparities: precipitation variability exerts strongest constraints on Henan and Anhui, whereas Shandong Jiangsu exhibit weaker dependencies. In Beijing–Tianjin–Hebei, March temperature emerges as critical determinant variability. These findings underscore need tailored adaptation strategies, such enhancing water-use efficiency inland provinces optimizing agronomic practices coastal regions. With its dual ability to resolve pixel-scale dynamics disentangle drivers, HHHWheatYield1km represents resource precision agriculture evidence-based policymaking face changing climate.

Language: Английский

Citations

0
PSeqNet: A crop phenology monitoring model accounting for phenological associations DOI

Qiyu Tian,

Hao Jiang, Renhai Zhong

et al.

ISPRS Journal of Photogrammetry and Remote Sensing, Journal Year: 2025, Volume and Issue: 225, P. 257 - 274

Published: May 5, 2025

Language: Английский

Citations

0
Advancing Corn Yield Mapping in Kenya Through Transfer Learning DOI Creative Commons

Ahaan Bohra,

Sophie Nottmeyer,

Chenchen Ren

et al.

Remote Sensing, Journal Year: 2025, Volume and Issue: 17(10), P. 1717 - 1717

Published: May 14, 2025

Crop yield mapping is essential for food security and policy making. Recent machine learning (ML) deep (DL) methods have achieved impressive accuracy in crop estimation. However, these models require numerous training samples that are scarce regions with underdeveloped infrastructure. Furthermore, domain shifts between different spatial prevent DL trained one region from being directly applied to another without adaptation. This effect particularly pronounced significant climate environmental variations such as the U.S. Kenya. To address this issue, we propose using fine-tuning-based transfer learning, which learns general associations predictors response variables data-abundant source then fine-tunes model on data-scarce target domain. We assess model’s performance estimating corn yields Kenya (target domain) (source domain). Feature variables, including time-series vegetation indices (VIs) sequential meteorological both domains, used pre-train fine-tune neural network model. The fine-tuned data 5 years (2019–2023) tested leave-one-year-out cross validation. DNN achieves an overall R2 of 0.632—higher than U.S.-only Kenya-only baselines—but paired significance tests show no aggregate difference, though a statistically gain does occur 2023 under anomalous heat conditions. These results demonstrate fine-tuning can reliably learned representations across continents and, certain climatic scenarios, meaningful improvements.

Language: Английский

Citations

0
The mixed effects of recent cover crop adoption on U.S. cropland productivity DOI Creative Commons
David B. Lobell, Stefania Di Tommaso, Qu Zhou

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 25, 2024

Abstract Farmers in the United States have rapidly expanded use of cover crops (CC), with national CC area nearly doubling since 2012. Despite many benefits that motivate public subsidies, questions remain about potential downsides. Using satellite observations from over 100,000 fields, half which recently adopted CC, we demonstrate led to: (i) declines average yields for corn and soybean, by ~3% ~2%, respectively; (ii) delays sowing (4 days) soybean (3 days); (iii) reduced damages wet spring 2019, fields only as likely to experience prevented planting non-CC fields. appears reduce important aspects farmer risk conditions but increase them dry conditions. Timely cash crop deserves emphasis moving forward, show eliminating would yield penalties roughly 50% 90% soybean.

Language: Английский

Citations

0