Early Classification for Agricultural Monitoring from Satellite Time Series
Technical University of Munich（慕尼黑工业大学）；Institut de Recherche en Informatique et Systèmes Aléatoires (IRISA)（信息与随机系统研究所）；LETG-Rennes（雷恩地球与环境科学实验室）；Université de Bretagne Sud（南布列塔尼大学）
Marc Rußwurm, Romain Tavenard, Sébastien Lefèvre, Marco Körner
In this work, we introduce a recently developed early classification mechanism to satellite-based agricultural monitoring. It augments existing classification models by an additional stopping probability based on the previously seen information. This mechanism is end-to-end trainable and derives its stopping decision solely from the observed satellite data. We show results on field parcels in central Europe where sufficient ground truth data is available for an empiric evaluation of the results with local phenological information obtained from authorities. We observe that the recurrent neural network outfitted with this early classification mechanism was able to distinguish the many of the crop types before the end of the vegetative period. Further, we associated these stopping times with evaluated ground truth information and saw that the times of classification were related to characteristic events of the observed plants' phenology.
Phenology curve estimation via a mixed model representation of functional principal components: Characterizing time series of satellite-derived vegetation indices
AGSPNet: A framework for parcel-scale crop fine-grained semantic change detection from UAV high-resolution imagery with agricultural geographic scene constraints
Hunan University of Science and Technology（湖南科技大学）
Satellite monitoring uncovers progress but large disparities in doubling crop yields
Mortenson Center in Global Engineering & Resilience, University of Colorado Boulder（科罗拉多大学博尔德分校莫滕森全球工程与韧性中心）；Better Planet Lab, University of Colorado Boulder（科罗拉多大学博尔德分校更美好星球实验室）；University of Colorado Boulder（科罗拉多大学博尔德分校）
On the Generalization of Agricultural Drought Classification from Climate Data
Deutsches Zentrum für Luft- und Raumfahrt (DLR)（德国航空航天中心）；Ludwig-Maximilians-Universität München（慕尼黑大学）；Columbia University（哥伦比亚大学）；Max Planck Institute for Biogeochemistry（马克斯·普朗克生物地球化学研究所）；Michael-Stifel-Center Jena for Data-driven and Simulation Science（耶拿迈克尔·斯蒂费尔数据驱动与模拟科学中心）；University of Bremen（不来梅大学）
Farm-LightSeek: An Edge-centric Multimodal Agricultural IoT Data Analytics Framework with Lightweight LLMs
School of Computer Science and Artificial Intelligence, Wuhan University of Technology（武汉理工大学计算机科学与人工智能学院）；School of Engineering, Swinburne University of Technology（斯威本科技大学工程学院）；School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）；School of Computing, Engineering and Mathematical Sciences, La Trobe University（拉筹伯大学计算、工程与数学科学学院）
CBAM-STN-TPS-YOLO: Enhancing Agricultural Object Detection through Spatially Adaptive Attention Mechanisms
1 Department of Computer Science；Engineering, Texas A\&M University, College Station, TX, USA 2 Department of Statistics, Texas A\&M University, College Station, TX, USA satvikpraveen\；2 Department of Statistics, Texas A\&M University, College Station, TX, USA satvikpraveen\
Improvement in Land Cover and Crop Classification based on Temporal Features Learning from Sentinel-2 Data Using Recurrent-Convolutional Neural Network (R-CNN)
University of Pittsburgh（匹兹堡大学）；University of Minnesota - Twin Cities（明尼苏达大学-双城分校）；Colorado State University（科罗拉多州立大学）；University of Maryland, College Park（马里兰大学学院市分校）
Harvesting AlphaEarth: Benchmarking the Geospatial Foundation Model for Agricultural Downstream Tasks
Department of Earth System Science and Center on Food Security and the Environment, Stanford University, USA（地球系统科学系和食品安全与环境中心，斯坦福大学，美国）；Corteva Agriscience™, USA（科特维亚农业科学公司，美国）
TinyNina: A Resource-Efficient Edge-AI Framework for Sustainable Air Quality Monitoring via Intra-Image Satellite Super-Resolution
ADAPT Research Centre, Dublin, Ireland（ADAPT研究中心，都柏林，爱尔兰）；School of Computer Science, Technological University Dublin, Ireland（都柏林科技大学计算机科学学院，爱尔兰）；School of Computer Science, University College Dublin, Ireland（都柏林大学学院计算机科学学院，爱尔兰）；School of Computer Science and Statistics, Trinity College Dublin（都柏林圣三一学院计算机科学与统计学院）
Generating Synthetic Satellite Imagery With Deep-Learning Text-to-Image Models -- Technical Challenges and Implications for Monitoring and Verification
Berliner Hochschule für Technik（柏林应用技术大学）；Princeton University（普林斯顿大学）；Einstein Center Digital Future（爱因斯坦数字未来中心）
Monitoring the Impacts of a Tailings Dam Failure Using Satellite Images
Colorado School of Mines（科罗拉多矿业大学）
利用卫星图像监测溃坝情况为第一反应者提供了有效的早期干预管理。同样重要的是，要监测淹没区的时空变化，以跟踪灾后恢复情况。2019年1月25日，位于巴西Brumadinho的Córrego do Feijão铁矿的尾矿坝倒塌。这场灾难造成230多人死亡，30人失踪，造成数十亿美元的损失。本研究使用哨兵2号卫星图像绘制淹没区地图，并评估和描绘受溃坝影响的土地利用和土地覆盖情况。这些图像对应于1月22日（崩溃前3天）和2月2日（崩溃后7天）的数据捕获。该地区的卫星图像在灾难发生之前和之后进行了分类，采用了机器学习算法。为了有足够的土地覆盖类型来验证算法的质量和准确性，定义了7类：矿山，森林，建筑物，河流，农业，清水和草地。开发的分类算法产生了很高的准确性（99%）的图像之前崩溃。本文使用两种不同的模型来确定土地覆盖影响，1）通过使用“之后”图像中的训练网络，以及2）通过创建第二个网络，在“之后”图像的点的子集中进行训练，然后比较两个训练网络的土地覆盖结果。在第一个模型中，将训练好的网络应用于“之后”的图像，准确率仍然很高（86%），但低于使用第二个模型（98%）。这一战略可通过利用公开提供的卫星信息以较低的成本用于监测和评估，在发生大坝坍塌或预算较大的情况下，可通过飞越有关地区获得更高分辨率和更快的数据。
Early Yield Prediction for Sugar Beet Fields using Satellite Data -- Learnings from Specialized Vision Transformers
Center for Artificial Intelligence and Robotics, Technical University of Applied Sciences Wuerzburg-Schweinfurt（人工智能与机器人中心，维尔茨堡-施韦因富特应用技术大学）；Bielefeld University（比勒费尔德大学）；green spin GmbH（绿旋有限公司）
Using Game Engines and Machine Learning to Create Synthetic Satellite Imagery for a Tabletop Verification Exercise
Berliner Hochschule für Technik（柏林技术应用科学大学）；Program on Science and Global Security, Princeton University（普林斯顿大学科学与全球安全项目）；Einstein Center Digital Future, Berlin（柏林爱因斯坦数字未来中心）
