.png){kind=icon}
.png){kind=icon}
Return
Simulating cropping sequences using earth observation data
.png){kind=icon}
OA
AI
DOI：10.1016/j.compag.2021.106330.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Model-based studies of agricultural systems often rely on the analyst defining realistic crop sequences. This usually involves relying on a few 'typical rotations' that are used in baseline scenarios. These may not account for the variation in farming practices across a region, however, as farmer decision making about which crops to grow is influenced by a combination of economic, environmental and social drivers. We describe and test an approach for generating random realisations of plausible crop sequences based on observed data as quantified by earth observation. Our approach combines crop classification data with a series of crop management rules that reflect the advice followed by farmers (e.g. to reduce the chance of crop-pests and disease). We adapt the approach to generate crop sequences specific to regions and soil type. This demonstrates how the method can be adapted to generate crop sequences typical of a study area of interest.
Keywords:
Crop rotations
Land Cover (R) plus: Crops
Modelling
Crop management
Baseline scenario modelling
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
8.9
Papers:
10.0K
Citations:
4.8W