Tianfang Xu
Utah State University
Recent Activity
ABSTRACT:
This resource is a deposit of the data and codes used in the reference below:
Xu, T., Guan, K,, Peng, B., Wei, S. and Zhao, L. (2021) Machine Learning-Based Modeling of Spatio-Temporally Varying Responses of Rainfed Corn Yield to Climate, Soil, and Management in the U.S. Corn Belt. Front. Artif. Intell. 4:647999. doi: 10.3389/frai.2021.64799
We used random forest to provide in-season prediction of county-wise rainfed corn yield in the U.S. Corn Belt by integrating various predictors including climate, soil properties, and management data such as planting date.
ABSTRACT:
Preferred citation:
Xu, T., Deines, J., Kendall, A., Basso, B., and Hyndman, DW. 2019. Addressing Challenges for Mapping Irrigated Fields in Subhumid Temperate Regions by Integrating Remote Sensing and Hydroclimatic Data. Remote Sensing.
We developed annual, 30-m resolution maps of irrigated corn and soybeans for southwestern Michigan from 2001 to 2016 using a machine learning method (random forest). Please see Xu et al. 2019 for full details. The rasters are in UINT 8 format, with 0 indicates rainfed, 1 indicates irrigated, and 3 indicates masked (not row crops according to NLCD before 2007 and not corn or soybeans according to CDL since 2007).
Contact
| (Log in to send email) |
| All | 0 |
| Collection | 0 |
| Resource | 0 |
| App Connector | 0 |
Created: Feb. 9, 2019, 9:58 p.m.
Authors: Tianfang Xu · Jillian M Deines · Anthony Kendall · Bruno Basso · David William Hyndman
ABSTRACT:
Preferred citation:
Xu, T., Deines, J., Kendall, A., Basso, B., and Hyndman, DW. 2019. Addressing Challenges for Mapping Irrigated Fields in Subhumid Temperate Regions by Integrating Remote Sensing and Hydroclimatic Data. Remote Sensing.
We developed annual, 30-m resolution maps of irrigated corn and soybeans for southwestern Michigan from 2001 to 2016 using a machine learning method (random forest). Please see Xu et al. 2019 for full details. The rasters are in UINT 8 format, with 0 indicates rainfed, 1 indicates irrigated, and 3 indicates masked (not row crops according to NLCD before 2007 and not corn or soybeans according to CDL since 2007).
Created: April 3, 2021, 10:46 p.m.
Authors: Xu, Tianfang · Kaiyu Guan · Bin Peng · Shiqi Wei · Lei Zhao
ABSTRACT:
This resource is a deposit of the data and codes used in the reference below:
Xu, T., Guan, K,, Peng, B., Wei, S. and Zhao, L. (2021) Machine Learning-Based Modeling of Spatio-Temporally Varying Responses of Rainfed Corn Yield to Climate, Soil, and Management in the U.S. Corn Belt. Front. Artif. Intell. 4:647999. doi: 10.3389/frai.2021.64799
We used random forest to provide in-season prediction of county-wise rainfed corn yield in the U.S. Corn Belt by integrating various predictors including climate, soil properties, and management data such as planting date.