Cropland De-Agriculturalization and De-Fooding Monitoring Based on Multi-Source Remote Sensing Data

DOI

10.2991/978-94-6463-910-0_12How to use a DOI?

Keywords

Farmland; De-agrarianization; Non-food; Target detection; Change detection; Deep learning

Abstract

With economic development and scientific and technological progress, China’s agriculture has made remarkable achievements, and its agricultural production capacity has increased significantly, guaranteeing national food security. However, agricultural development is also faced with the challenge of non-farming and non-food cultivation of arable land. Industrialization and population reduction have led to the conversion of a large amount of arable land to non-farm use or non-food crop cultivation, affecting food production capacity and the balance of agricultural structure. In particular, “non-food” cultivation—i.e., the conversion of arable land to forest land, garden land, or other uses not associated with basic food crops—has become a prominent trend, threatening food security. In order to obtain farmland information and monitor the changes of farmland in a timely manner, this paper takes Suixian County in Hubei as the study area, and utilizes 2020 and 2023 Jilin-1 remote sensing images, combines the cloud GPU platform to train a deep learning model, adopts Yolov5 for non-agriculturalization target detection, and analyzes the fine-grained changes of farmland with the MSCANet network. The results show that Yolov5 can basically recognize photovoltaic land, wasteland and new buildings, and MSCANet is more advantageous than traditional methods in terms of accuracy and computational efficiency. The study shows that remote sensing technology has an important value in farmland monitoring, and multi-source remote sensing combined with deep learning provides a scientific basis for monitoring the non-agriculturalization of arable land and supports policy-making in areas such as land use planning, food security management, and ecological protection.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Yueran Zheng
PY  - 2025
DA  - 2025/12/15
TI  - Cropland De-Agriculturalization and De-Fooding Monitoring Based on Multi-Source Remote Sensing Data
BT  - Proceedings of the 2025 2nd International Symposium on Agricultural Engineering and Biology (ISAEB 2025)
PB  - Atlantis Press
SP  - 105
EP  - 117
SN  - 2468-5747
UR  - https://doi.org/10.2991/978-94-6463-910-0_12
DO  - 10.2991/978-94-6463-910-0_12
ID  - Zheng2025
ER  -