[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2313":3},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":6,"published_at":11,"category":12,"cover_url":9,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":24,"tags":28,"view_count":34,"doi":35,"paper":36,"created_at":50},2313,"Artificial Intelligence For Climate-Resilient Plants: Emerging Ai Approaches For Predicting Drought, Salinity And Temperature Stress.","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22724439","Abstract Climate change is creating serious problems for agriculture by increasing drought, soil salinity, and extreme temperatures. These stresses affect plant growth, development, crop yield, and global food security. Traditional methods used to study plant responses to stress are often time-consuming, labour-intensive, and difficult to use for large numbers of plants. Artificial intelligence (AI) is becoming an important tool for studying and predicting plant responses to changing environmental conditions. AI can analyse large amounts of data collected through plant phenotyping, remote sensing, environmental sensors, and molecular studies. This review focuses on recent AI approaches used to predict plant responses to drought, salinity, and temperature stress from 2016 to 2026. Machine learning, deep learning, computer vision, thermal imaging, and hyperspectral imaging can help in early detection and prediction of plant stress. Recent developments are moving beyond simple stress identification towards predicting crop performance and stress tolerance. The combination of AI with high-throughput phenotyping and multi-omics can help identify stress-tolerant crop varieties and support climate-resilient breeding. However, challenges related to data quality, limited field validation, unclear model predictions, and poor performance across different environments still remain. Future research should develop reliable and explainable AI models for sustainable agriculture and improved crop production under climate change.","摘要 气候变化正通过加剧干旱、土壤盐渍化和极端温度，给农业带来严重问题。这些胁迫影响植物生长、发育、作物产量和全球粮食安全。用于研究植物胁迫响应的传统方法往往耗时、费力，且难以应用于大量植物。人工智能（AI）正成为研究和预测植物对环境条件变化响应的重要工具。AI可以分析通过植物表型分析、遥感、环境传感器和分子研究收集的大量数据。本文综述聚焦于2016年至2026年间用于预测植物对干旱、盐分和温度胁迫响应的近期AI方法。机器学习、深度学习、计算机视觉、热成像和高光谱成像有助于植物胁迫的早期检测和预测。近期发展正超越简单的胁迫识别，转向预测作物表现和胁迫耐受性。AI与高通量表型分析和多组学的结合有助于识别耐胁迫作物品种，并支持气候韧性育种。然而，数据质量、田间验证有限、模型预测不明确以及在不同环境中表现不佳等挑战仍然存在。未来研究应开发可靠且可解释的AI模型，以促进气候变化下的可持续农业和作物生产提升。",null,"Zenodo (CERN European Organization for Nuclear Research)","2026-09-30T00:00:00Z","论文",25,false,71,{"impact":17,"substance":18,"depth":19,"authority":20,"freshness":21,"relevant":22,"comment":23},18,20,17,13,3,1,"系统综述AI预测干旱、盐碱与高温胁迫的研究进展，方法覆盖机器学习、深度学习与高光谱成像，对气候韧性育种有参考价值，但属综述类论文且距发布已逾两周，时效性偏弱。",[25,26],{"name":10,"url":6},{"name":10,"url":27},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.22724438",[29,30,31,32,33],"智慧农业","农业人工智能","气候韧性","遥感监测","作物育种",0,"10.5281\u002Fzenodo.22724439",{"doi":35,"openalex_id":37,"authors":38,"venue":10,"cited_by_count":34,"oa_url":6,"card":43,"direction":47,"ingested_from":49},"W7212377743",[39,41],{"name":40,"orcid":9},"Aruna Nangare",{"name":42,"orcid":9},"Vaishali Wankhede",{"tldr":44,"method":45,"finding":46,"direction":47,"opportunity":48},"综述2016-2026年AI预测植物干旱、盐碱和温度胁迫响应的进展。","机器学习、深度学习、计算机视觉、热成像与高光谱成像结合表型组和多组学数据。","AI已从简单胁迫识别转向预测作物表现与耐逆性，但数据质量、田间验证和跨环境泛化仍是瓶颈。","农业遥感与作物表型","可解释AI与高通量表型、多组学融合，用于跨环境耐逆品种预测与气候韧性育种。","openalex","2026-09-13T23:30:17.636747Z"]