Abstract
A long-term, high-resolution cropland dataset plays an essential part in accurately and systematically understanding the mechanisms that drive cropland change and its effect on biogeochemical processes. However, current widely used spatially explicit cropland databases are developed according to a simple downscaling model and are associated with low resolution. By combining historical county-level cropland archive data with natural and anthropogenic variables, we developed a random forest model to spatialize the cropland distribution in the Tuojiang River Basin (TRB) during 1911–2010, using a resolution of 30 m. The reconstruction results showed that the cropland in the TRB increased from 1.13 × 104 km2 in 1911 to 1.81 × 104 km2. In comparison with satellite-based data for 1980, the reconstructed dataset approximated the remotely sensed cropland distribution. Our cropland map could capture cropland distribution details better than three widely used public cropland datasets, due to its high spatial heterogeneity and improved spatial resolution. The most critical factors driving the distribution of TRB cropland include nearby-cropland, elevation, and climatic conditions. This newly reconstructed cropland dataset can be used for long-term, accurate regional ecological simulation, and future policymaking. This novel reconstruction approach has the potential to be applied to other land use and cover types via its flexible framework and modifiable parameters.
Highlights
The land use and cover change (LUCC) process has undergone drastic changes due to the population boom over the past century, during which rising demands for food and fiber have led to expansion of agricultural lands
The major objectives of this paper are: (1) to develop an random forest (RF) classifier workflow for historical cropland reconstruction; (2) to reconstruct a cropland dataset that describes the Tuojiang River Basin (TRB) during 1911–2010 with 30 m resolution; (3) to validate the reconstruction results based on remotely sensed land use data and three public datasets; and (4) to examine the proximate drivers of cropland distribution
This paper proposed an RF model workflow for historical cropland reconstruction
Summary
The land use and cover change (LUCC) process has undergone drastic changes due to the population boom over the past century, during which rising demands for food and fiber have led to expansion of agricultural lands. As one of the predominant land use types [1], cropland serves as an important carbon budget component and has significant impacts on biogeochemical processes, such as food production, global change, regional ecosystem services, and biodiversity [2,3,4]. Most currently used cropland datasets are developed at the large scale with medium- or low-resolution, and lack high-precision spatial information. This produces an important research gap because long-term, spatially explicit land-use maps are critical input data for many biogeochemical land-surface models (e.g., ORCHIDEE, DLEM) [7,8], which are used for the IPCC report and the annual global carbon budget estimate [9]. There is an urgent need for a long-term, accurate cropland dataset that can improve ecological simulation accuracy and support detailed ecological analyses
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
