The impact of climate change on China's food security considering artificial intelligence level: Based on XGBoost and RIME-CNN-LSTM-ATT models

IF 10.9 1区环境科学与生态学 Q1 ENGINEERING, ENVIRONMENTAL

Resources Conservation and Recycling Pub Date : 2025-08-23 DOI:10.1016/j.resconrec.2025.108539

Qian Li , Hong Chen , Ruyin Long , Qingqing Sun , Zhiping Huang

{"title":"The impact of climate change on China's food security considering artificial intelligence level: Based on XGBoost and RIME-CNN-LSTM-ATT models","authors":"Qian Li , Hong Chen , Ruyin Long , Qingqing Sun , Zhiping Huang","doi":"10.1016/j.resconrec.2025.108539","DOIUrl":null,"url":null,"abstract":"<div><div>Artificial intelligence (AI) plays a pivotal role in addressing the challenges of climate change and food security (FS). The current state of FS in China is evaluated from the perspectives of consumption and production. Six machine learning models are employed to explore the relationship among climate change, AI level and FS. A novel FS prediction model is proposed based on RIME-CNN-LSTM-ATT algorithm to predict FS trends under multiple scenarios. The results reveal that: The SHAP values of AI are all positive, indicating the significant potential of AI in enhancing FS. In major grain-producing region, temperature accounts for 58.6 % of the influence on FS, representing the primary driver. Rainfall and sunshine are identified as the main threats to FS in grain producing-consuming balance area. Under the baseline, SSP1+RCP2.6, and SSP2+RCP4.5 scenarios, China’s overall FS level will increase 2.30 %, 2.93 %, and 2.37 % by 2035, respectively, but decline by 6.68 % under SSP5+RCP8.5.</div></div>","PeriodicalId":21153,"journal":{"name":"Resources Conservation and Recycling","volume":"224 ","pages":"Article 108539"},"PeriodicalIF":10.9000,"publicationDate":"2025-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Resources Conservation and Recycling","FirstCategoryId":"93","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0921344925004094","RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, ENVIRONMENTAL","Score":null,"Total":0}

引用次数: 0

Abstract

Artificial intelligence (AI) plays a pivotal role in addressing the challenges of climate change and food security (FS). The current state of FS in China is evaluated from the perspectives of consumption and production. Six machine learning models are employed to explore the relationship among climate change, AI level and FS. A novel FS prediction model is proposed based on RIME-CNN-LSTM-ATT algorithm to predict FS trends under multiple scenarios. The results reveal that: The SHAP values of AI are all positive, indicating the significant potential of AI in enhancing FS. In major grain-producing region, temperature accounts for 58.6 % of the influence on FS, representing the primary driver. Rainfall and sunshine are identified as the main threats to FS in grain producing-consuming balance area. Under the baseline, SSP1+RCP2.6, and SSP2+RCP4.5 scenarios, China’s overall FS level will increase 2.30 %, 2.93 %, and 2.37 % by 2035, respectively, but decline by 6.68 % under SSP5+RCP8.5.

查看原文本刊更多论文

基于XGBoost和RIME-CNN-LSTM-ATT模型的气候变化对中国粮食安全的影响

人工智能（AI）在应对气候变化和粮食安全挑战方面发挥着关键作用。从消费和生产两个角度对中国农产品生产现状进行了评价。采用6个机器学习模型探讨气候变化、AI水平和FS之间的关系。提出了一种基于RIME-CNN-LSTM-ATT算法的多场景FS预测模型。结果表明：人工智能的SHAP值均为正，表明人工智能在增强FS方面具有显著的潜力。在主产区，温度对FS的影响占58.6%，是主要驱动因素。降雨和日照是粮食产销平衡区粮食安全的主要威胁。在SSP1+RCP2.6和SSP2+RCP4.5情景下，到2035年中国总体FS水平分别上升2.30%、2.93%和2.37%，而在SSP5+RCP8.5情景下，中国总体FS水平下降6.68%。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Resources Conservation and Recycling 环境科学-工程：环境

CiteScore

22.90

自引率

6.10%

发文量

625

审稿时长

23 days

期刊介绍： The journal Resources, Conservation & Recycling welcomes contributions from research, which consider sustainable management and conservation of resources. The journal prioritizes understanding the transformation processes crucial for transitioning toward more sustainable production and consumption systems. It highlights technological, economic, institutional, and policy aspects related to specific resource management practices such as conservation, recycling, and resource substitution, as well as broader strategies like improving resource productivity and restructuring production and consumption patterns. Contributions may address regional, national, or international scales and can range from individual resources or technologies to entire sectors or systems. Authors are encouraged to explore scientific and methodological issues alongside practical, environmental, and economic implications. However, manuscripts focusing solely on laboratory experiments without discussing their broader implications will not be considered for publication in the journal.