SITSMamba for Crop Classification based on Satellite Image Time Series
Wuhan University(武汉大学);State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing(遥感信息工程国家重点实验室);School of Remote Sensing and Information Engineering(遥感信息工程学院)
Satellite image time series (SITS) data provides continuous observations over time, allowing for the tracking of vegetation changes and growth patterns throughout the seasons and years. Numerous deep learning (DL) approaches using SITS for crop classification have emerged recently, with the latest approaches adopting Transformer for SITS classification. However, the quadratic complexity of self-attention in Transformer poses challenges for classifying long time series. While the cutting-edge Mamba architecture has demonstrated strength in various domains, including remote sensing image interpretation, its capacity to learn temporal representations in SITS data remains unexplored. Moreover, the existing SITS classification methods often depend solely on crop labels as supervision signals, which fails to fully exploit the temporal information. In this paper, we proposed a Satellite Image Time Series Mamba (SITSMamba) method for crop classification based on remote sensing time series data. The proposed SITSMamba contains a spatial encoder based on Convolutional Neural Networks (CNN) and a Mamba-based temporal encoder. To exploit richer temporal information from SITS, we design two branches of decoder used for different tasks. The first branch is a crop Classification Branch (CBranch), which includes a ConvBlock to decode the feature to a crop map. The second branch is a SITS Reconstruction Branch that uses a Linear layer to transform the encoded feature to predict the original input values. Furthermore, we design a Positional Weight (PW) applied to the RBranch to help the model learn rich latent knowledge from SITS. We also design two weighting factors to control the balance of the two branches during training. The code of SITSMamba is available at: https://github.com/XiaoleiQinn/SITSMamba.
Can SAM recognize crops? Quantifying the zero-shot performance of a semantic segmentation foundation model on generating crop-type maps using satellite imagery for precision agriculture
California Crop Yield Benchmark: Combining Satellite Image, Climate, Evapotranspiration, and Soil Data Layers for County-Level Yield Forecasting of Over 70 Crops
University of California, Davis(加州大学戴维斯分校);Texas A&M University-Corpus Christi(德克萨斯A&M大学-科斯蒂西);AI Institute for Food Systems(人工智能食品系统研究所)
Crossmodal learning for Crop Canopy Trait Estimation
Department of Computer Engineering, Iowa State University, Ames, IA, USA(计算机工程系,爱荷华州立大学);Department of Mechanical Engineering, Iowa State University, Ames, IA, USA(机械工程系,爱荷华州立大学)
Cropland PAtteRNS: Parallel Dimensional Attention Networks and Attention to Dataset Disparity for Crop Segmentation in Satellite Imagery Time Series Data
Weakly Supervised Framework Considering Multi-temporal Information for Large-scale Cropland Mapping with Satellite Imagery
School of Geosciences and Info-Physics, Central South University(中南大学地球科学与信息物理学院);The 27th Research Institute, China Electronic Technology Group Corporation(中国电子科技集团公司第二十七研究所)
Boosting Crop Classification by Hierarchically Fusing Satellite, Rotational, and Contextual Data
Centro Nacional de Inteligencia Artificial (CENIA)(国家人工智能中心);European Commission, Joint Research Centre (JRC)(欧盟委员会联合研究中心);Technical University of Munich(慕尼黑工业大学)
Agave crop segmentation and maturity classification with deep learning data-centric strategies using very high-resolution satellite imagery
Coordinación General de Innovación Gubernamental, del Gobierno de Jalisco(哈利斯科州政府政府创新总协调局);ITESO—The Jesuit University of Guadalajara(瓜达拉哈拉伊泰索耶稣会大学);Universidad Autónoma de Guadalajara(瓜达拉哈拉自治大学)
Detecting Crop Burning in India using Satellite Data
在世界许多地方,特别是南亚,农作物残留物燃烧是空气污染的主要来源。政策制定者、从业人员和研究人员已投资于衡量影响和制定干预措施,以减少燃烧。然而,衡量燃烧的影响或减少燃烧的干预措施的有效性需要关于燃烧发生地点的数据。从成本和可行性两方面来看,在实地收集这些数据都具有挑战性。我们利用印度旁遮普省农作物残留物燃烧的地面监测数据,探讨使用可访问的卫星图像是否可以更有效地检测燃烧。具体而言,我们使用了具有高时间分辨率(高达每日)的3 m PlanetScope数据以及公开的Sentinel-2数据,这些数据具有每周的时间分辨率,但光谱信息的深度更大。在分析了不同光谱波段和燃烧指数单独分离燃烧和未燃烧地块的能力之后,我们建立了一个随机森林模型,其中确定了提供最大分离性的模型,并利用地面验证数据评估了模型性能。考虑到测量所带来的挑战,我们82%的整体模型准确度是有利的。基于这一过程的见解,我们讨论了从卫星图像检测作物残留燃烧的技术挑战,以及测量燃烧和政策干预的影响的挑战。
Using Machine Learning to generate an open-access cropland map from satellite images time series in the Indian Himalayan Region
Empa, Swiss Federal Laboratories for Materials Science and Technology(瑞士联邦材料科学与技术实验室);École Polytechnique Fédérale de Lausanne(洛桑联邦理工学院);Swiss Data Science Center, ETH Zurich and EPFL(瑞士数据科学中心(苏黎世联邦理工学院和洛桑联邦理工学院))
Bayesian aggregation improves traditional single image crop classification approaches
Center for Computational and Data-Intensive Science and Engineering (CDISE)(计算与数据密集型科学与工程中心(CDISE));Skolkovo Institute of Science and Technology (Skoltech)(斯科尔科沃科学技术学院(Skoltech))
UAV and Machine Learning Based Refinement of a Satellite-Driven Vegetation Index for Precision Agriculture
Politecnico di Torino(都灵理工大学);Politecnico Interdepartmental Centre for Service Robotics(都灵理工大学跨部门服务机器人中心);Università degli Studi di Torino(都灵大学);Institute of Electronics, Computer and Telecommunication Engineering of the National Research Council of Italy(意大利国家研究委员会电子、计算机与电信工程研究所)
精准农业被认为是追求低投入、高效率和可持续农业的基本途径。为了实现这一目标,需要对当地作物状况进行可靠和最新的描述。遥感,特别是卫星图像,已证明是作物制图、监测和疾病评估的宝贵工具。然而,免费提供的低分辨率或中等分辨率的卫星图像在具体的农业应用方面显示出一些限制,例如,农作物是一排排种植的。事实上,在这个框架内,卫星的输出可能会受到行内覆盖的影响,从而提供关于作物状况的不准确信息。本文提出了一种新的卫星图像细化框架,基于深度学习技术,该技术充分利用了无人机(UAV)机载多光谱传感器获取的高分辨率图像中的信息。为了训练卷积神经网络,仅需要单个无人机驱动的数据集,使得所提出的方法简单且具有成本效益。Serralunga d 'Alba(意大利北部)的葡萄园被选为验证目的的案例研究。细化卫星驱动的归一化差异植被指数(NDVI)地图,在葡萄生长季节的四个不同时期获得的,被证明是更好地描述作物状况相对于原始数据集的相关性分析和方差分析。此外,使用基于K-均值的分类器,3级葡萄园活力地图是有益的,从NDVI地图,这是一个有价值的工具,为种植者。
FLNet: Flood-Induced Agriculture Damage Assessment using Super Resolution of Satellite Images
Annam.AI CoE, MoE, Indian Institute of Technology Ropar, Punjab, India(Annam.AI联合研究所、教育部、印度理工学院罗帕尔分校);Department of Mathematical Sciences, Rajiv Gandhi Institute of Petroleum Technology, Jais, UP, India(数学科学系、拉贾吉安石油技术学院);Department of Computer Science and Engineering, Indian Institute of Technology Ropar, Punjab, India(计算机科学与工程系、印度理工学院罗帕尔分校)
Towards more efficient agricultural practices via transformer-based crop type classification
Gobierno del estado de Jalisco(哈利斯科州政府);TecMM Unidad Zapopan(TecMM萨波潘分部);Climate Change AI(气候变化人工智能);Kabarak University(卡巴拉大学);Aspia Space(阿斯皮亚航天);Columbia University(哥伦比亚大学)
Crop mapping from image time series: deep learning with multi-scale label hierarchies
ETH Zurich(苏黎世联邦理工学院);Agroscope(瑞士农业研究中心);Federal Office for Agriculture, Switzerland(瑞士联邦农业办公室);University of Zurich(苏黎世大学)
本文的目的是通过对卫星图像时间序列进行分类来绘制农业作物图。农业领域的专家使用以分层树结构组织的作物类型标签,其中粗类(如果园)被细分为细类(如苹果,梨,葡萄藤等)。我们开发了一种作物分类方法,利用这种专家知识,并显着提高稀有作物类型的映射。三级标签层次结构被编码在卷积递归神经网络(convRNN)中,使得对于每个像素,模型以不同的粒度级别预测三个标签。这种端到端可训练的分层网络架构允许模型学习稀有类的联合特征表示(例如,苹果,梨)在较粗糙的水平(例如,果园),从而提高细粒度级别的分类性能。此外,以不同粒度进行标记还可以根据分类分数调整输出;因为具有高置信度的粗标签有时比细粒度但非常不确定的标签更适用于农业实践。我们在一个新的,我们公开的大型数据集上验证了所提出的方法。ZueriCrop覆盖了瑞士苏黎世州和图尔高州50 km x 48 km的区域,共有116,000个独立的田地,跨越48个作物类别,以及来自Sentinel-2的28,000个(多时相)图像块。我们将我们提出的分层convRNN模型与几个基线进行了比较,包括为不平衡类分布设计的方法。分层方法在F1评分中至少优于9.9个百分点。
University of Delaware(特拉华大学);University of Louisiana at Lafayette(路易斯安那大学拉斐特分校);University of Connecticut(康涅狄格大学);University of Oklahoma(俄克拉荷马大学);Mississippi State University(密西西比州立大学);Louisiana State University(路易斯安那州立大学);LSU AgCenter(路易斯安那州立大学农业中心);Tulane University(杜兰大学)
Benchmarking for Practice: Few-Shot Time-Series Crop-Type Classification on the EuroCropsML Dataset
Technical University of Munich (TUM)(慕尼黑技术大学);TUM School of Engineering and Design(慕尼黑技术大学工程与设计学院);Department of Aerospace and Geodesy(航空航天与大地测量系);Chair of Remote Sensing Technology(遥感技术教授团);Munich Data Science Institute (MDSI)(慕尼黑数据科学研究所);ELLIS Unit Jena(耶纳ELLIS单元);University of Jena(耶纳大学);ETH Zurich(苏黎世联邦理工学院);Department of Mathematics(数学系);Zuse Institute Berlin(柏林Zuse研究所)