Research on Irrigation Decision-Making for Xinjiang Cotton Based on Genetic Algorithm and Reinforcement Learning

Zhenxiang Han; Tengfei Feng; Weihong Sun; Wanxia Yang; Zhuo Yu; Meiwei Lin; Guangzhou Li; Liang He

doi:10.2991/978-94-6463-746-5_9

<Previous Article In Volume

Next Article In Volume>

Research on Irrigation Decision-Making for Xinjiang Cotton Based on Genetic Algorithm and Reinforcement Learning

Authors

Zhenxiang Han¹, Tengfei Feng¹, Weihong Sun³, Wanxia Yang⁴, Zhuo Yu³, Meiwei Lin³, Guangzhou Li¹, Liang He¹^{, 2}^{, *}

¹School of Computer Science and Technology, Xinjiang University, Urumqi, 830017, China

²Department of Electronic Engineering, National Research Center for Information Science and Technology, Tsinghua University, Beijing, 100084, China

³School of Agricultural Engineering, Jiangsu University, Zhenjiang, 212013, China

⁴School of Mechanical and Electrical Engineering, Gansu Agricultural University, Lanzhou, 730070, China

^*Corresponding author. Email: heliang@mail.tsinghua.edu.cn

Corresponding Author

Liang He

Available Online 27 May 2025.

DOI: 10.2991/978-94-6463-746-5_9 How to use a DOI?
Keywords: Genetic Algorithm; Reinforcement Learning; DSSAT Model; Irrigation System; Subsurface Drip Irrigation
Abstract: To improve water use efficiency and cotton yield in the field cotton planting of Changji, Xinjiang, this paper proposes an intelligent irrigation decision-making scheme based on genetic algorithms and reinforcement learning. The 2023 cotton planting data were used to validate the accuracy of the CROPGRO-Cotton model. After ensuring the crop model’s ability to simulate field conditions, a decision-making model based on DSSAT and genetic algorithms was proposed. Reinforcement learning was then used to optimize the crossover and mutation rates of the genetic algorithm. The experimental results show that the irrigation strategy based on DSSAT and genetic algorithms significantly improved both water use efficiency and cotton yield. After optimization with reinforcement learning, both water use efficiency and yield were further improved. The optimal irrigation decision, as simulated, involved 10 irrigations and a total irrigation amount of 454mm, with a cotton yield and water use efficiency of 6266 kg·hm^-2 and 1.26 kg·m^-3, respectively. Compared to the field experiment with the same irrigation amount and the genetic algorithm, the cotton yield was 596 kg·hm^-2 and 22 kg·hm^-2 higher, respectively. This study provides new theoretical insights and practical value for cotton irrigation decision-making in the Changji region of Xinjiang.
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)

<Previous Article In Volume

Next Article In Volume>

Volume Title: Proceedings of the 2025 International Conference on Agriculture and Resource Economy (ICARE 2025)
Series: Advances in Biological Sciences Research
Publication Date: 27 May 2025
ISBN: 978-94-6463-746-5
ISSN: 2468-5747
DOI: 10.2991/978-94-6463-746-5_9 How to use a DOI?
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.

Cite this article

ris enw bib

TY  - CONF
AU  - Zhenxiang Han
AU  - Tengfei Feng
AU  - Weihong Sun
AU  - Wanxia Yang
AU  - Zhuo Yu
AU  - Meiwei Lin
AU  - Guangzhou Li
AU  - Liang He
PY  - 2025
DA  - 2025/05/27
TI  - Research on Irrigation Decision-Making for Xinjiang Cotton Based on Genetic Algorithm and Reinforcement Learning
BT  - Proceedings of the 2025 International Conference on Agriculture and Resource Economy (ICARE 2025)
PB  - Atlantis Press
SP  - 71
EP  - 84
SN  - 2468-5747
UR  - https://doi.org/10.2991/978-94-6463-746-5_9
DO  - 10.2991/978-94-6463-746-5_9
ID  - Han2025
ER  -

download .riscopy to clipboard