[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-2352":3,"related-2352":80},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"content":9,"source_name":10,"source_url":8,"published_at":11,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":15,"score_detail":16,"sources":23,"tags":25,"primary_topic":31,"secondary_topics":36,"classification":43,"search_phrases":74,"slug":77,"view_count":78,"doi":8,"paper":8,"created_at":79},2352,"AI种稻 永丰村300亩稻田'算'出丰收——四川农业大学水稻专属AI大模型试点","https:\u002F\u002Fcountry.scol.com.cn\u002Fshtml\u002Fscncrb\u002F20260910\u002F1089253.html","9月7日四川眉山市东坡区永丰村300亩稻田首次试用水稻专属AI大模型管理。马均团队把几十年栽培专业知识、永丰村大田生产数据'喂养'模型，通过土壤墒情、水位、虫情等传感器回传数据，输出分田块、分时段农事建议。系统联合电子科技大学开展跨学科协作，从永丰到崇州、新都多点试验。",null,"[![Image 1](https:\u002F\u002Fcountry.scol.com.cn\u002Fpaperdata\u002Fscncrb\u002F20260910\u002F427adbfcc1abcc628278a76234ca5b58.jpg)](https:\u002F\u002Fcountry.scol.com.cn\u002Fpaperdata\u002Fscncrb\u002F20260910\u002F427adbfcc1abcc628278a76234ca5b58.jpg) 杨志远在田间巡查（实景与AI种稻意象合成图）。\n\n●永丰村 300 亩试点田首次应用水稻专属AI大模型管理，从“凭经验看田”转向靠数据辅助决策\n\n ●AI测算分析出9月15日为最佳开镰日期，预计亩产量为880—895公斤\n\n ●崇州、新都等地同步探索，“算力守田”在“天府粮仓”多点开花□四川农村日报全媒体 记者 袁宇君 文\u002F图\n\n 9月7日，眉山市东坡区太和镇永丰村里，连片稻田翻着金浪。种粮大户邵国东站在田埂上，望着即将开镰的300亩稻田，满脸笑意。不少游客、研学团队正在田边“打卡”拍照，在他们眼中，这片稻田和别处的高产稻田没有区别。\n\n 没有遍地显眼的机器人，也没有密密麻麻的新设备，很少有人知道，这片看似普通的稻田，是村里首批应用水稻专属AI大模型管理的试点田。\n\n 看不见的北斗卫星在天上定位，传感器埋在田间，AI藏在小程序后台，从插秧、水肥调控到病虫害预警，这一季水稻的田间管理，从“凭经验看田”，转向了靠数据、靠算法辅助决策。丰收在望的稻浪底下，一场“算力守田”的种粮试验，在永丰村落地。\n把栽培知识装进AI大模型\n\n “我以为AI种稻时，田里会摆满新奇设备，到了地头才发现完全不是这么回事。”记者抛出疑问。\n\n 四川农业大学水稻栽培专家马均解释，这恰恰是这套技术的特别之处：北斗在天上、无人机按需出动、AI大模型在云端，肉眼看不见，但农户打开“东坡巡田”小程序就能连上整套系统。\n\n 这片 300 亩试点田，是四川省水稻新品种新技术中试研发平台今年的核心成果展示田，由马均团队主导搭建了水稻专属AI大模型。团队做的第一件事，是把几十年积累的水稻栽培专业知识、永丰村多年的大田生产数据，包括生育期规律、土壤基线、气象历史、水肥方案、农机作业记录、历年产量品质等，一一入库“喂养”模型。\n\n 土壤墒情传感器、水位监测、虫情诱捕设备，加上卫星遥感、无人机巡田、人工下地复核，多渠道持续回传苗情、水情、灾情数据。AI根据实时数据自动判读生育阶段和长势，匹配地块属性、品种特性、天气预报，输出分田块、分时段的补水、追肥、防控农事建议。\n\n “不是替代农民全自动种稻，更像24小时在岗的专业参谋。”邵国东直呼，这一季种得省心。\n\n 不少种业从业者也盯上了这片试点田。浙江勿忘农股份有限公司的张乐乐专程来到田间，300亩试点田里种了好几个他们选育的新品种。“很多好品种潜力强，但配套栽培技术跟不上，优势就发挥不出来，这次相当于给新品种配上了专属的精准栽培体系，是非常难得的试错场景。”张乐乐说。\n\n 值得一提的是，这 300亩试点田的收割最佳时间和预估产量，也是 AI 算出来的。“我们将无人机‘扫田’的数据输入后，AI分析出9月15日是最佳开镰日期，预计亩产量为880—895公斤。”四川农业大学副教授、四川东坡永丰水稻科技小院院长杨志远告诉记者。\n\n永丰村凭什么先“跑”起来\n\n 为什么 AI 种稻首片试点田落在永丰村？答案不仅仅在于算法，更在于这片田多年攒下的“硬底子”。\n\n 作为全省水稻新品种新技术中试研发平台的核心基地、“天府粮仓”建设标杆村，永丰村不是从零起步做AI，前期已经完成了高标准农田建设、全程机械化操作、数字化监测等铺垫工作。\n\n 在永丰村，连片规整的高标准农田宜机化全覆盖，耕种收全流程机械化早已跑通，当地水稻平均亩产稳定在780公斤；田间物联网监测点位数字化覆盖率达到92%，水质、水深、墒情、虫情、气象数据常年积累，再叠加马均团队20多年600多个品种、数十项栽培技术的中试台账，这些凑齐了训练农业AI 最稀缺、最宝贵的高质量田间数据集。\n\n 换而言之，永丰村人早就入局了智慧农业：先修良田、配农机、铺好感知网络、跑通数字化台账，再往上叠加AI决策层。村干部、种植户、农技员早就习惯用手机看田块数据、远程调度，“东坡巡田”小程序有现成的用户基础，农户接受门槛低，天然适合做AI种稻试点。\n\n 也正因此，马均团队选择先控制成本、小范围验证，目前仅完成300亩试点。杨志远透露，专用AI模型“高质量数据‘喂’得越多，模型迭代进化越快，用户用起来越精准”。\n\n “我们的模型现阶段仍处于学习迭代期，难免会给出不合理建议。”杨志远坦言，现阶段模型输出的农事方案必须经过农技人员人工把关校验，“但随着模型的快速迭代，失误率会急速降低，离媲美农艺专家的目标并不遥远。”\n\n迭代训练AI种稻将多点开花\n\n 为了融合作物栽培机理和算法能力，目前四川农业大学团队正联合电子科技大学专家开展跨学科协作，共同训练、打磨这款水稻垂直领域AI大模型：农学团队负责把关农业逻辑、田间试验设计、标签数据质量，电子科大团队负责算法架构、多源数据融合、模型轻量化、成本优化。\n\n “持续‘投喂’数据，模型就最懂这片稻田；以后导入川南、川东、川北等不同稻区的本地化数据，就能适配不同生态区的种稻场景。”杨志远介绍，当前核心目标是优先打磨模型可靠性、降低部署成本，再逐步扩大示范面积。\n\n 放眼全川，永丰村不是四川唯一探索点位，“算力守田”正在“天府粮仓”多点开花。\n\n 成都崇州市已连续举办两届“天府粮仓”人工智能水稻种植挑战赛，AI决策团队和资深种粮“老把式”同田竞技。去年5月，由中国农业科学院都市农业研究所研发的“人工智能水稻种植决策智能体”为4名农户提供AI辅助种植指导，与6名传统种植农户展开了对比试验。\n\n 成都市新都区军屯省级智慧无人示范农场600亩核心区，由省农科院朱从桦团队打造，围绕稻麦轮作、AI作物模型+精准灌溉、无人巡田、高温稳产管控方向建设，走出了一条智慧生产路径。\n\n 今年四川省委一号文件提出，顺应当前新一轮科技革命与产业变革加速发展态势，发展智慧农业，支持有条件的地方建设智慧农业引领区。从永丰村的300亩水稻试点，到崇州的人工智能水稻种植挑战赛，再到新都的无人农场——算力，正成为“天府粮仓”的“新农具”。","四川农村日报 | 2026-09-10","2026-09-10T00:00:00Z","报道",10,false,76,{"impact":17,"substance":18,"depth":19,"authority":13,"freshness":20,"relevant":21,"comment":22},22,21,17,6,1,"四川农业大学水稻专属AI大模型在永丰村300亩试点落地，含最佳开镰期与亩产预估等实质数据，并串联崇州、新都多点探索，是智慧农业垂直模型应用的省级代表性案例。",[24],{"name":10,"url":6},[26,27,28,29,30],"智慧农业","农业人工智能","水稻","天府粮仓","AI大模型",{"code":32,"slug":33,"name":28,"path":34,"parent_code":35},"A1","rice","\u002Ftopic\u002Ffield-crops\u002Frice","A",[37],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},"I2","agricultural-ai","农业AI与大模型","\u002Ftopic\u002Fdigital-agriculture\u002Fagricultural-ai","I",{"status":44,"locked":14,"version":45,"method":46,"evidence":47},"classified","2026-10-22.2","rules",{"candidates":48,"agricultural_evidence":51},[49,56,62,69],{"code":32,"score":50,"supported":51,"title":52,"abstract":54,"tags":55},23,true,[28,53],"稻田",[28,53],[28],{"code":38,"score":57,"supported":51,"title":58,"abstract":60,"tags":61},12,[59],"大模型",[59],[27],{"code":63,"score":64,"supported":51,"title":65,"abstract":66,"tags":68},"H2",3,[],[67],"土壤",[],{"code":70,"score":21,"supported":14,"title":71,"abstract":72,"tags":73},"I1",[],[],[26],[75,76],"农业人工智能 天府粮仓 智慧农业 AI大模型","农业人工智能 天府粮仓","农业人工智能天府粮仓智慧农业AI大模型-2352",2,"2026-09-14T00:06:26.216594Z",{"total":20,"page":21,"page_size":20,"items":81},[82,120,187,271,330,412],{"id":83,"title":84,"url":85,"summary":86,"summary_zh":8,"content":87,"source_name":88,"source_url":8,"published_at":89,"category":12,"cover_url":8,"hotness":13,"is_selected":14,"score":90,"score_detail":91,"sources":96,"tags":98,"primary_topic":99,"secondary_topics":100,"classification":102,"search_phrases":117,"slug":118,"view_count":21,"doi":8,"paper":8,"created_at":119},2260,"眉山市东坡区永丰村300亩稻田应用水稻专属AI大模型管理 AI测算9月15日开镰","https:\u002F\u002Fwww.agri.cn\u002Fzx\u002Fxxlb\u002Fsc\u002F202609\u002Ft20260911_8870726.htm","9月7日,眉山市东坡区太和镇永丰村300亩试点田首次应用水稻专属AI大模型管理,AI测算分析出9月15日为最佳开镰日期,预计亩产量为880-895公斤。由四川农业大学马均团队主导搭建水稻专属AI大模型,北斗在天上、无人机按需出动、AI大模型在云端。","**●永丰村300亩试点田首次应用水稻专属AI大模型管理，从“凭经验看田”转向靠数据辅助决策**\n\n**●AI测算分析出9月15日为最佳开镰日期，预计亩产量为880—895公斤**\n\n**●崇州、新都等地同步探索，“算力守田”在“天府粮仓”多点开花**\n\n9月7日，眉山市东坡区太和镇永丰村里，连片稻田翻着金浪。种粮大户邵国东站在田埂上，望着即将开镰的300亩稻田，满脸笑意。不少游客、研学团队正在田边“打卡”拍照，在他们眼中，这片稻田和别处的高产稻田没有区别。\n\n没有遍地显眼的机器人，也没有密密麻麻的新设备，很少有人知道，这片看似普通的稻田，是村里首批应用水稻专属AI大模型管理的试点田。\n\n看不见的北斗卫星在天上定位，传感器埋在田间，AI藏在小程序后台，从插秧、水肥调控到病虫害预警，这一季水稻的田间管理，从“凭经验看田”，转向了靠数据、靠算法辅助决策。丰收在望的稻浪底下，一场“算力守田”的种粮试验，在永丰村落地。\n\n把栽培知识装进AI大模型\n\n“我以为AI种稻时，田里会摆满新奇设备，到了地头才发现完全不是这么回事。”记者抛出疑问。\n\n四川农业大学水稻栽培专家马均解释，这恰恰是这套技术的特别之处：北斗在天上、无人机按需出动、AI大模型在云端，肉眼看不见，但农户打开“东坡巡田”小程序就能连上整套系统。\n\n这片300亩试点田，是四川省水稻新品种新技术中试研发平台今年的核心成果展示田，由马均团队主导搭建了水稻专属AI大模型。团队做的第一件事，是把几十年积累的水稻栽培专业知识、永丰村多年的大田生产数据，包括生育期规律、土壤基线、气象历史、水肥方案、农机作业记录、历年产量品质等，一一入库“喂养”模型。\n\n土壤墒情传感器、水位监测、虫情诱捕设备，加上卫星遥感、无人机巡田、人工下地复核，多渠道持续回传苗情、水情、灾情数据。AI根据实时数据自动判读生育阶段和长势，匹配地块属性、品种特性、天气预报，输出分田块、分时段的补水、追肥、防控农事建议。\n\n“不是替代农民全自动种稻，更像24小时在岗的专业参谋。”邵国东直呼，这一季种得省心。\n\n不少种业从业者也盯上了这片试点田。浙江勿忘农股份有限公司的张乐乐专程来到田间，300亩试点田里种了好几个他们选育的新品种。“很多好品种潜力强，但配套栽培技术跟不上，优势就发挥不出来，这次相当于给新品种配上了专属的精准栽培体系，是非常难得的试错场景。”张乐乐说。\n\n值得一提的是，这300亩试点田的收割最佳时间和预估产量，也是AI算出来的。“我们将无人机‘扫田’的数据输入后，AI分析出9月15日是最佳开镰日期，预计亩产量为880—895公斤。”四川农业大学副教授、四川东坡永丰水稻科技小院院长杨志远告诉记者。\n\n永丰村凭什么先“跑”起来\n\n为什么AI种稻首片试点田落在永丰村？答案不仅仅在于算法，更在于这片田多年攒下的“硬底子”。\n\n作为全省水稻新品种新技术中试研发平台的核心基地、“天府粮仓”建设标杆村，永丰村不是从零起步做AI，前期已经完成了高标准农田建设、全程机械化操作、数字化监测等铺垫工作。\n\n在永丰村，连片规整的高标准农田宜机化全覆盖，耕种收全流程机械化早已跑通，当地水稻平均亩产稳定在780公斤；田间物联网监测点位数字化覆盖率达到92%，水质、水深、墒情、虫情、气象数据常年积累，再叠加马均团队20多年600多个品种、数十项栽培技术的中试台账，这些凑齐了训练农业AI最稀缺、最宝贵的高质量田间数据集。\n\n换而言之，永丰村人早就入局了智慧农业：先修良田、配农机、铺好感知网络、跑通数字化台账，再往上叠加AI决策层。村干部、种植户、农技员早就习惯用手机看田块数据、远程调度，“东坡巡田”小程序有现成的用户基础，农户接受门槛低，天然适合做AI种稻试点。\n\n也正因此，马均团队选择先控制成本、小范围验证，目前仅完成300亩试点。杨志远透露，专用AI模型“高质量数据‘喂’得越多，模型迭代进化越快，用户用起来越精准”。\n\n“我们的模型现阶段仍处于学习迭代期，难免会给出不合理建议。”杨志远坦言，现阶段模型输出的农事方案必须经过农技人员人工把关校验，“但随着模型的快速迭代，失误率会急速降低，离媲美农艺专家的目标并不遥远。”\n\n迭代训练AI种稻将多点开花\n\n为了融合作物栽培机理和算法能力，目前四川农业大学团队正联合电子科技大学专家开展跨学科协作，共同训练、打磨这款水稻垂直领域AI大模型：农学团队负责把关农业逻辑、田间试验设计、标签数据质量，电子科大团队负责算法架构、多源数据融合、模型轻量化、成本优化。\n\n“持续‘投喂’数据，模型就最懂这片稻田；以后导入川南、川东、川北等不同稻区的本地化数据，就能适配不同生态区的种稻场景。”杨志远介绍，当前核心目标是优先打磨模型可靠性、降低部署成本，再逐步扩大示范面积。\n\n放眼全川，永丰村不是四川唯一探索点位，“算力守田”正在“天府粮仓”多点开花。\n\n成都崇州市已连续举办两届“天府粮仓”人工智能水稻种植挑战赛，AI决策团队和资深种粮“老把式”同田竞技。去年5月，由中国农业科学院都市农业研究所研发的“人工智能水稻种植决策智能体”为4名农户提供AI辅助种植指导，与6名传统种植农户展开了对比试验。\n\n成都市新都区军屯省级智慧无人示范农场600亩核心区，由省农科院朱从桦团队打造，围绕稻麦轮作、AI作物模型+精准灌溉、无人巡田、高温稳产管控方向建设，走出了一条智慧生产路径。\n\n今年四川省委一号文件提出，顺应当前新一轮科技革命与产业变革加速发展态势，发展智慧农业，支持有条件的地方建设智慧农业引领区。从永丰村的300亩水稻试点，到崇州的人工智能水稻种植挑战赛，再到新都的无人农场——算力，正成为“天府粮仓”的“新农具”。（四川农村日报全媒体记者袁宇君文\u002F图）","中国农业农村信息网","2026-09-10T16:00:00Z",72,{"impact":92,"substance":93,"depth":19,"authority":13,"freshness":94,"relevant":21,"comment":95},18,20,7,"水稻专属AI大模型首次落地试点，含最佳开镰期与亩产预测等实质数据，多方信源支撑，具行业示范价值。",[97],{"name":88,"url":85},[26,27,28,29,30],{"code":32,"slug":33,"name":28,"path":34,"parent_code":35},[101],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":103},{"candidates":104,"agricultural_evidence":51},[105,109,113],{"code":32,"score":93,"supported":51,"title":106,"abstract":107,"tags":108},[28,53],[28],[28],{"code":38,"score":57,"supported":51,"title":110,"abstract":111,"tags":112},[59],[59],[27],{"code":70,"score":21,"supported":14,"title":114,"abstract":115,"tags":116},[],[],[26],[75,76],"农业人工智能天府粮仓智慧农业AI大模型-2260","2026-09-13T00:04:03.246936Z",{"id":121,"title":122,"url":123,"summary":124,"summary_zh":125,"content":8,"source_name":126,"source_url":123,"published_at":127,"category":128,"cover_url":8,"hotness":13,"is_selected":14,"score":129,"score_detail":130,"sources":134,"tags":136,"primary_topic":139,"secondary_topics":140,"classification":142,"search_phrases":162,"slug":165,"view_count":166,"doi":167,"paper":168,"created_at":186},4802,"A Privacy-Preserving Federated Learning Framework for Paddy Leaf Disease Detection Using an Enhanced Pretrained Novel EfficientNet-Lite4 Model","https:\u002F\u002Fdoi.org\u002F10.15832\u002Fankutbd.1837705","The correct and prompt detection of leaf diseases in paddy crops remains essential for protecting agricultural output and yield stability and reducing major losses that occur during severe disease outbreaks. The widespread use of conventional centralized machine learning techniques becomes impractical for real-world agricultural applications, as their effectiveness diminishes under three main conditions: data privacy limitations, delayed transmission of information, along with reduced performance accuracy from non-independent and identically distributed (non-IID) data properties across different agro-climatic regions. This research develops a decentralized diagnostic system which combines Federated Learning with an Enhanced Pretrained Novel EfficientNet-Lite4 model designed for paddy leaf disease classification. The Paddy Doctor dataset served as training material for the system which contained 16,225 RGB images that classified 12 disease types alongside healthy categories. The proposed model reached 98.7% classification accuracy and 98.5% precision and 98.6% F1-score while maintaining a final loss of 0.21 after 100 communication rounds. The system underwent field testing which demonstrated its ability to generate accurate diagnostic results in real time in various working conditions. The study demonstrates how privacy preserving AI-based paddy disease management works in practice and recommends local agricultural institutions to build decentralized learning systems. The suggested system will give farmers direct access to field level decision support and facilitate the creation of sustainable digital pest management systems required to ensure food supply.","正确且及时地检测水稻作物叶片病害，对于保护农业产出和产量稳定、减少病害严重暴发期间发生的重大损失仍然至关重要。传统集中式机器学习技术的广泛使用在现实农业应用中变得不切实际，因为在三种主要条件下其有效性会下降：数据隐私限制、信息传输延迟，以及不同农业气候区域间非独立同分布（non-IID）数据特性导致的性能准确率降低。本研究开发了一种去中心化诊断系统，将联邦学习与一种增强的预训练新型高效网络模型EfficientNet-Lite4相结合，用于水稻叶片病害分类。Paddy Doctor数据集作为该系统的训练材料，包含16,225张RGB图像，涵盖12种病害类型以及健康类别。所提出的模型在100轮通信后达到了98.7%的分类准确率、98.5%的精确率和98.6%的F1分数，同时最终损失保持在0.21。该系统经过实地测试，证明其能够在各种工作条件下实时生成准确的诊断结果。该研究展示了基于隐私保护人工智能的水稻病害管理如何在实践中运作，并建议地方农业机构构建去中心化学习系统。所建议的系统将为农民提供直接的田间决策支持，并促进建立确保粮食供应所需的可持续数字病虫害管理系统。","Tarım Bilimleri Dergisi","2026-10-12T00:00:00Z","论文",80,{"impact":92,"substance":17,"depth":92,"authority":131,"freshness":132,"relevant":21,"comment":133},13,9,"将联邦学习与轻量级EfficientNet-Lite4结合用于水稻叶病识别，兼顾隐私保护与98.7%高精度，对智慧农业落地有参考价值。",[135],{"name":126,"url":123},[26,27,28,137,138],"病虫害识别","联邦学习",{"code":32,"slug":33,"name":28,"path":34,"parent_code":35},[141],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":143},{"candidates":144,"agricultural_evidence":51},[145,151,158],{"code":32,"score":146,"supported":51,"title":147,"abstract":149,"tags":150},15,[148],"paddy",[28,148],[28],{"code":38,"score":57,"supported":51,"title":152,"abstract":153,"tags":157},[],[154,155,156],"机器学习","machine learning","decision support",[27,137,138],{"code":70,"score":21,"supported":14,"title":159,"abstract":160,"tags":161},[],[],[26],[163,164],"Paddy Doctor 数据集 水稻病害","EfficientNet-Lite4 水稻叶片病害","PaddyDoctor数据集水稻病害-4802",0,"10.15832\u002Fankutbd.1837705",{"doi":167,"openalex_id":169,"authors":170,"venue":126,"cited_by_count":166,"oa_url":177,"card":178,"direction":184,"ingested_from":185},"W7221522859",[171,174],{"name":172,"orcid":173},"B Johnson","https:\u002F\u002Forcid.org\u002F0009-0009-8281-4051",{"name":175,"orcid":176},"Chandrakumar Thangavel","https:\u002F\u002Forcid.org\u002F0000-0002-1186-5988","https:\u002F\u002Fdergipark.org.tr\u002Fen\u002Fdownload\u002Farticle-file\u002F5486058",{"tldr":179,"method":180,"finding":181,"direction":182,"opportunity":183},"提出联邦学习结合改进EfficientNet-Lite4的水稻叶片病害检测框架，兼顾隐私与精度。","联邦学习+预训练EfficientNet-Lite4，用Paddy Doctor","12类病害分类准确率达98.7%，100轮通信后损失0.21，支持实时诊断。","农业人工智能与决策模型","可探索非IID数据下联邦聚合优化与轻量化模型在边缘设备的部署研究。","智慧农业 \u002F 农业物联网","openalex","2026-10-13T23:30:08.809781Z",{"id":188,"title":189,"url":190,"summary":191,"summary_zh":8,"content":8,"source_name":192,"source_url":190,"published_at":193,"category":128,"cover_url":8,"hotness":13,"is_selected":14,"score":194,"score_detail":195,"sources":198,"tags":200,"primary_topic":203,"secondary_topics":204,"classification":211,"search_phrases":232,"slug":235,"view_count":21,"doi":236,"paper":237,"created_at":270},4500,"Integrating UAV-Based Remote Sensing and Deep Learning for Early Detection of Bacterial Leaf Blight in Rice","https:\u002F\u002Fdoi.org\u002F10.21203\u002Frs.3.rs-11163942\u002Fv1","Integrating UAV-Based Remote Sensing and Deep Learning for Early Detection of Bacterial Leaf Blight in Rice。Research Square","Research Square","2026-10-08T00:00:00Z",74,{"impact":92,"substance":93,"depth":92,"authority":13,"freshness":196,"relevant":21,"comment":197},8,"将无人机遥感与深度学习结合用于水稻白叶枯病早期检测，方法有创新、结论具应用价值，但属预印本且为细分技术进展，适合进入主题聚合而非头条精选。",[199],{"name":192,"url":190},[26,27,28,201,202],"遥感","病害检测",{"code":32,"slug":33,"name":28,"path":34,"parent_code":35},[205,206],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"code":207,"slug":208,"name":209,"path":210,"parent_code":42},"I3","remote-sensing","遥感与农情监测","\u002Ftopic\u002Fdigital-agriculture\u002Fremote-sensing",{"status":44,"locked":14,"version":45,"method":46,"evidence":212},{"candidates":213,"agricultural_evidence":51},[214,218,223,228],{"code":32,"score":57,"supported":51,"title":215,"abstract":216,"tags":217},[33],[33],[28],{"code":38,"score":57,"supported":51,"title":219,"abstract":221,"tags":222},[220],"deep learning",[220],[27],{"code":207,"score":57,"supported":51,"title":224,"abstract":226,"tags":227},[225],"remote sensing",[225],[201],{"code":70,"score":21,"supported":14,"title":229,"abstract":230,"tags":231},[],[],[26],[233,234],"无人机遥感 水稻 白叶枯病","深度学习 水稻病害 早期检测","无人机遥感水稻白叶枯病-4500","10.21203\u002Frs.3.rs-11163942\u002Fv1",{"doi":236,"openalex_id":238,"authors":239,"venue":192,"cited_by_count":166,"oa_url":190,"card":8,"direction":269,"ingested_from":185},"W7221055917",[240,243,246,248,250,253,255,257,260,262,264,266],{"name":241,"orcid":242},"Carlito B. Balingbing","https:\u002F\u002Forcid.org\u002F0000-0002-3672-9253",{"name":244,"orcid":245},"Dmytro Chebotarov","https:\u002F\u002Forcid.org\u002F0000-0003-1351-9453",{"name":247,"orcid":8},"Ian  Carlo Perilla",{"name":249,"orcid":8},"Stephen Klassen",{"name":251,"orcid":252},"Nancy Castilla","https:\u002F\u002Forcid.org\u002F0000-0002-9143-4933",{"name":254,"orcid":8},"Raphael  Gabriel Carvajal",{"name":256,"orcid":8},"Kendrix Ortega",{"name":258,"orcid":259},"Joseph M. Sandro","https:\u002F\u002Forcid.org\u002F0000-0002-8311-2299",{"name":261,"orcid":8},"Nurmi Pangesti",{"name":263,"orcid":8},"Caesar Arloo R. Centeno",{"name":265,"orcid":8},"Arnel Rala",{"name":267,"orcid":268},"Li-Yu  Daisy Liu","https:\u002F\u002Forcid.org\u002F0000-0001-6997-8101","农业遥感与作物表型","2026-10-09T23:30:18.390549Z",{"id":272,"title":273,"url":274,"summary":275,"summary_zh":276,"content":8,"source_name":277,"source_url":274,"published_at":278,"category":128,"cover_url":8,"hotness":13,"is_selected":14,"score":279,"score_detail":280,"sources":283,"tags":285,"primary_topic":288,"secondary_topics":289,"classification":291,"search_phrases":311,"slug":314,"view_count":78,"doi":315,"paper":316,"created_at":329},4431,"A multimodal deep learning for rice crop health monitoring using vegetation index feature selection","https:\u002F\u002Fdoi.org\u002F10.1038\u002Fs41598-026-74895-5","Crop health monitoring is essential for sustaining agricultural productivity and ensuring stable production, particularly in major crop-producing regions that face challenges due to climate variability, resource constraints, and spatial heterogeneity. Traditional methods struggle to effectively integrate spatial heterogeneity and environmental variability from multi-source remote sensing (RS) data. To address this problem, the proposed work explores the role of satellite imagery in monitoring rice crop health with the help of Vegetation Indices (VIs) under the impact of changing weather conditions. Multi-temporal Sentinel-1 and Sentinel-2 satellite data were acquired from a rice cultivation field in Gorakhpur, Uttar Pradesh, India, during three Kharif growing seasons (2023-2025). In this work, we propose a supervised MI-based feature selection framework employing Otsu’s adaptive thresholding for selection of VIs that strongly determine the health of rice crop. To ensure data integrity, cloud-contaminated observations were systematically excluded through a two-stage cleaning process. Further, we propose a multimodal deep learning (DL) framework that fuses a Swin Transformer (Swin-T) backbone for spatial feature extraction from vegetation index imagery with a Multi-Layer Perceptron (MLP) for structured numerical modeling of meteorological variables. The proposed framework achieved 94.05% accuracy on an independent held-out test set and a mean accuracy of \\(92.12 \\pm 5.28\\) % under 10-fold cross-validation, consistently outperforming competing hybrid deep learning baselines. These results highlight that integrating transformer-based spatial representations with environmental information provides an efficient approach for rice crop health classification. The proposed framework can be extended to multi-region crop monitoring by incorporating additional vegetation index modalities and diverse climatic conditions.","作物健康监测对于维持农业生产力、保障稳定生产至关重要，尤其是在面临气候变异性、资源约束和空间异质性挑战的主要作物产区。传统方法难以有效整合多源遥感（RS）数据中的空间异质性和环境变异性。为解决这一问题，本研究探索了卫星影像在天气条件变化影响下借助植被指数（VIs）监测水稻作物健康的作用。研究在印度北方邦戈勒克布尔的稻田中，于三个水稻生长季（2023—2025年）获取了多时相Sentinel-1和Sentinel-2卫星数据。在本研究中，我们提出了一种基于互信息（MI）的监督式特征选择框架，采用Otsu自适应阈值法筛选对水稻作物健康具有强判别能力的植被指数。为确保数据完整性，通过两阶段清洗流程系统性地剔除了受云污染的观测数据。此外，我们提出了一种多模态深度学习（DL）框架，该框架融合了Swin Transformer（Swin-T）主干网络用于从植被指数影像中提取空间特征，以及多层感知机（MLP）用于气象变量的结构化数值建模。所提框架在独立留出测试集上达到了94.05%的准确率，在10折交叉验证下平均准确率为\\(92.12 \\pm 5.28\\)%，持续优于竞争的混合深度学习基线模型。这些结果表明，将基于Transformer的空间表征与环境信息相结合，为水稻作物健康分类提供了一种高效方法。所提框架可通过纳入更多植被指数模态和多样化气候条件，扩展至多区域作物监测。","Scientific Reports","2026-10-07T00:00:00Z",81,{"impact":92,"substance":17,"depth":92,"authority":281,"freshness":132,"relevant":21,"comment":282},14,"方法新颖、数据跨三个生长季且精度可靠，属农业遥感与AI交叉的细分领域进展，值得进入每日精选。",[284],{"name":277,"url":274},[26,27,28,286,287],"遥感监测","作物长势",{"code":32,"slug":33,"name":28,"path":34,"parent_code":35},[290],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":292},{"candidates":293,"agricultural_evidence":51},[294,298,303,307],{"code":32,"score":92,"supported":51,"title":295,"abstract":296,"tags":297},[33],[28,53,33],[28],{"code":38,"score":146,"supported":51,"title":299,"abstract":300,"tags":302},[220],[301,220],"深度学习",[27],{"code":207,"score":94,"supported":51,"title":304,"abstract":305,"tags":306},[],[201,225],[286],{"code":70,"score":21,"supported":14,"title":308,"abstract":309,"tags":310},[],[],[26],[312,313],"Sentinel-2 水稻 遥感监测","Swin Transformer 作物健康","Sentinel-2水稻遥感监测-4431","10.1038\u002Fs41598-026-74895-5",{"doi":315,"openalex_id":317,"authors":318,"venue":277,"cited_by_count":166,"oa_url":274,"card":324,"direction":269,"ingested_from":185},"W7220838898",[319,322],{"name":320,"orcid":321},"Shashank Gupta","https:\u002F\u002Forcid.org\u002F0000-0003-1291-7951",{"name":323,"orcid":8},"Shefali Arora Chouhan",{"tldr":325,"method":326,"finding":327,"direction":269,"opportunity":328},"融合Sentinel-1\u002F2植被指数与气象数据，用多模态深度学习监测水稻健康。","Sentinel-1\u002F2多时相数据、MI特征选择、Otsu阈值、Swin-T+M","独立测试准确率94.05%，10折交叉验证92.12%，优于混合基线。","可扩展至多区域多作物，探索更多植被指数模态与极端气候下的泛化能力。","2026-10-08T23:30:29.254071Z",{"id":331,"title":332,"url":333,"summary":334,"summary_zh":335,"content":8,"source_name":336,"source_url":333,"published_at":337,"category":128,"cover_url":8,"hotness":338,"is_selected":14,"score":90,"score_detail":339,"sources":341,"tags":345,"primary_topic":347,"secondary_topics":348,"classification":351,"search_phrases":396,"slug":399,"view_count":166,"doi":400,"paper":401,"created_at":411},4310,"Comprehensive remote sensing and machine learning framework for multi-regional rice yield forecasting under hydroclimatic variability in Sahelian Niger","https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23149579","It is crucial to forecast rice yields effectively in order to improve agricultural planning and resilience to climate change in the Sahel, where production is greatly affected by hydroclimatic variability. This research has developed an integrated framework combining remote sensing analysis and machine learning to assess the variability in rice production in Niamey, Dosso, Tillaberi and Diffa, in Niger, over the period 2010–2025. They combined Landsat-derived NDVI and EVI with parameters such as evapotranspiration, precipitation, temperature, humidity, solar radiation, soil moisture, cultivated area, year and season. We processed and harmonised the datasets using Google Earth Engine and Python. We then evaluated four regression algorithms separately, Random Forest (RF), k-nearest neighbours (KNN), support vector regression (SVR) and XGBoost (XGB), for each region. The correlation analysis revealed modest positive links between rice yield and the NDVI (r = 0.27) and the EVI (r = 0.14), while a strong correlation was observed between the NDVI and the EVI (r = 0.80). The vegetation indices showed marked seasonal and interannual variability, generally exhibiting higher values during the wet season. Model performance varied considerably from one region to another","在萨赫勒地区，有效预测水稻产量对于改善农业规划和增强气候变化适应能力至关重要，因为该地区的生产在很大程度上受到水文气候变率的制约。本研究开发了一个集成框架，将遥感分析与机器学习相结合，以评估尼日尔尼亚美、多索、蒂拉贝里和迪法在2010—2025年期间水稻产量的变异性。研究将基于Landsat的归一化植被指数（NDVI）和增强型植被指数（EVI）与蒸散发、降水、温度、湿度、太阳辐射、土壤水分、耕地面积、年份和季节等参数相结合。利用Google Earth Engine和Python对数据集进行了处理和协调。随后，针对每个地区分别评估了四种回归算法：随机森林（RF）、k近邻（KNN）、支持向量回归（SVR）和XGBoost（XGB）。相关分析显示，水稻产量与NDVI（r = 0.27）和EVI（r = 0.14）之间存在弱正相关，而NDVI与EVI之间则观察到强相关（r = 0.80）。植被指数表现出明显的季节性和年际变异性，通常在湿季呈现较高值。模型性能在不同地区之间差异显著。","Zenodo (CERN European Organization for Nuclear Research)","2026-10-05T00:00:00Z",25,{"impact":57,"substance":18,"depth":19,"authority":131,"freshness":132,"relevant":21,"comment":340},"基于Landsat植被指数与四种机器学习模型的多区域水稻产量预测研究，方法扎实、数据跨度长，但属区域性学术成果，对国内农业信息化有方法借鉴价值。",[342,343],{"name":336,"url":333},{"name":336,"url":344},"https:\u002F\u002Fdoi.org\u002F10.5281\u002Fzenodo.23149580",[26,27,28,346,201],"产量预测",{"code":32,"slug":33,"name":28,"path":34,"parent_code":35},[349,350],{"code":207,"slug":208,"name":209,"path":210,"parent_code":42},{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":352},{"candidates":353,"agricultural_evidence":51},[354,359,363,367,372,379,386,392],{"code":207,"score":355,"supported":51,"title":356,"abstract":357,"tags":358},16,[225],[201,225],[346,201],{"code":32,"score":146,"supported":51,"title":360,"abstract":361,"tags":362},[33],[28,33],[28],{"code":38,"score":146,"supported":51,"title":364,"abstract":365,"tags":366},[155],[154,155],[27],{"code":63,"score":20,"supported":51,"title":368,"abstract":369,"tags":371},[],[67,370],"soil",[],{"code":373,"score":20,"supported":51,"title":374,"abstract":375,"tags":378},"H3",[],[376,377],"蒸散发","evapotranspiration",[],{"code":380,"score":20,"supported":51,"title":381,"abstract":382,"tags":385},"H7",[],[383,384],"气候变化","climate change",[],{"code":387,"score":64,"supported":51,"title":388,"abstract":389,"tags":391},"J1",[],[390],"农业规划",[],{"code":70,"score":21,"supported":14,"title":393,"abstract":394,"tags":395},[],[],[26],[397,398],"尼日尔 水稻 遥感 产量预测","Landsat NDVI 水稻 机器学习","尼日尔水稻遥感产量预测-4310","10.5281\u002Fzenodo.23149579",{"doi":400,"openalex_id":402,"authors":403,"venue":336,"cited_by_count":166,"oa_url":333,"card":406,"direction":269,"ingested_from":185},"W7220391503",[404],{"name":405,"orcid":8},"Battula Vijaya Saradhi Halarou Saidou Souley",{"tldr":407,"method":408,"finding":409,"direction":269,"opportunity":410},"结合遥感植被指数与机器学习，预测尼日尔萨赫勒四地区2010–2025年水稻产量。","Landsat NDVI\u002FEVI 加气象土壤变量，GEE与Python处理，比较","NDVI\u002FEVI与产量仅弱相关，模型精度区域差异大，植被指数呈明显季节与年际波动。","可引入时序深度学习与迁移学习，解决跨区域泛化差及植被指数解释力弱的问题。","2026-10-06T23:30:20.077977Z",{"id":413,"title":414,"url":415,"summary":416,"summary_zh":417,"content":8,"source_name":418,"source_url":415,"published_at":419,"category":128,"cover_url":8,"hotness":13,"is_selected":14,"score":129,"score_detail":420,"sources":422,"tags":424,"primary_topic":426,"secondary_topics":427,"classification":430,"search_phrases":452,"slug":455,"view_count":78,"doi":456,"paper":457,"created_at":473},3164,"Spatiotemporal Deep Learning for Rice Plant Height Estimation from Multi-Temporal UAV RGB Imagery","https:\u002F\u002Fdoi.org\u002F10.3390\u002Fagriculture16182034","Accurate plant height estimation is important for monitoring crop growth and supporting precision agricultural management. Manual measurements are labor-intensive, while LiDAR-based methods are expensive and require complex processing. UAV photogrammetry provides a lower-cost alternative but remains challenging in flooded rice paddies because of canopy deformation and difficulties in terrain extraction. This study proposes Rice-STNet, a spatiotemporal deep learning framework for end-to-end rice plant height estimation using multi-temporal UAV RGB imagery. Rice-STNet integrates a convolutional neural network for spatial feature extraction, Time2Vec for temporal encoding, and a gated recurrent unit network for modeling temporal dependencies across observation dates. The framework was evaluated using field data collected from rice paddies over two growing seasons. Rice-STNet achieved an R2 of 0.97, a root mean squared error of 1.97 cm, and a mean absolute error of 1.14 cm. It outperformed random forest, support vector regression, a CNN-only baseline, and a UAV photogrammetry-based point-cloud approach. In addition, the framework generated high-resolution plant height maps for field-scale analysis of spatial growth variability. These results underscore the importance of jointly modeling spatial and temporal characteristics for continuously evolving crop traits. The proposed framework offers an accurate, scalable, and non-destructive solution for large-scale crop phenotyping and precision agriculture.","准确的株高估算对于监测作物生长和支持精准农业管理具有重要意义。人工测量劳动强度大，而基于激光雷达（LiDAR）的方法成本高昂且需要复杂的处理。无人机摄影测量提供了一种成本较低的替代方案，但在淹水稻田中仍面临挑战，原因在于冠层变形和地形提取困难。本研究提出了Rice-STNet，一种时空深度学习框架，用于利用多时相无人机RGB影像进行端到端水稻株高估算。Rice-STNet集成了用于空间特征提取的卷积神经网络、用于时间编码的Time2Vec，以及用于建模观测日期之间时间依赖关系的门控循环单元网络。该框架利用两个生长季从稻田采集的田间数据进行了评估。Rice-STNet取得了R²为0.97、均方根误差为1.97 cm、平均绝对误差为1.14 cm的结果。其性能优于随机森林、支持向量回归、仅使用CNN的基线方法以及基于无人机摄影测量的点云方法。此外，该框架生成了高分辨率株高图，用于田块尺度空间生长变异性分析。这些结果凸显了联合建模空间与时间特征对于持续变化的作物性状的重要性。所提出的框架为大规模作物表型分析和精准农业提供了一种准确、可扩展且非破坏性的解决方案。","Agriculture","2026-09-21T00:00:00Z",{"impact":92,"substance":17,"depth":92,"authority":131,"freshness":132,"relevant":21,"comment":421},"提出时空深度学习框架Rice-STNet，用多时相无人机RGB影像实现水稻株高高精度估算，方法新颖、数据跨两个生长季，对作物表型与精准农业有实用价值。",[423],{"name":418,"url":415},[26,27,28,201,425],"作物表型",{"code":32,"slug":33,"name":28,"path":34,"parent_code":35},[428,429],{"code":38,"slug":39,"name":40,"path":41,"parent_code":42},{"code":207,"slug":208,"name":209,"path":210,"parent_code":42},{"status":44,"locked":14,"version":45,"method":46,"evidence":431},{"candidates":432,"agricultural_evidence":51},[433,437,441,446],{"code":32,"score":92,"supported":51,"title":434,"abstract":435,"tags":436},[33],[28,53,33],[28],{"code":38,"score":146,"supported":51,"title":438,"abstract":439,"tags":440},[220],[301,220],[27],{"code":207,"score":196,"supported":51,"title":442,"abstract":443,"tags":445},[],[425,444],"crop phenotyping",[425,201],{"code":70,"score":94,"supported":51,"title":447,"abstract":448,"tags":451},[],[449,450],"精准农业","precision agriculture",[26],[453,454],"无人机 RGB 水稻株高","Rice-STNet 水稻表型","无人机RGB水稻株高-3164","10.3390\u002Fagriculture16182034",{"doi":456,"openalex_id":458,"authors":459,"venue":418,"cited_by_count":166,"oa_url":415,"card":468,"direction":269,"ingested_from":185},"W7213887432",[460,463,465],{"name":461,"orcid":462},"Weiguo Wang","https:\u002F\u002Forcid.org\u002F0009-0003-4028-9363",{"name":464,"orcid":8},"Noboru Noguchi",{"name":466,"orcid":467},"Liangliang Yang","https:\u002F\u002Forcid.org\u002F0000-0002-5055-3987",{"tldr":469,"method":470,"finding":471,"direction":269,"opportunity":472},"提出Rice-STNet时空深度学习框架，用多时相无人机RGB影像估算水稻株高。","CNN提取空间特征，Time2Vec编码时间，GRU建模时序依赖，两季稻田数据验","R²达0.97、RMSE 1.97cm，优于随机森林、SVR、纯CNN及点云方法。","可迁移至其他作物与多源遥感融合，探索轻量化模型及实时田间部署。","2026-09-22T23:30:18.545958Z"]