9 pages, Presented at 2018 INFORMS Conference on Business Analytics and Operations Research (Baltimore, MD, USA). One of the winning solutions to the 2018 Syngenta Crop Challenge
Crop yield is a highly complex trait determined by multiple factors such as genotype, environment, and their interactions. Accurate yield prediction requires fundamental understanding of the functional relationship between yield and these interactive factors, and to reveal such relationship requires both comprehensive datasets and powerful algorithms. In the 2018 Syngenta Crop Challenge, Syngenta released several large datasets that recorded the genotype and yield performances of 2,267 maize hybrids planted in 2,247 locations between 2008 and 2016 and asked participants to predict the yield performance in 2017. As one of the winning teams, we designed a deep neural network (DNN) approach that took advantage of state-of-the-art modeling and solution techniques. Our model was found to have a superior prediction accuracy, with a root-mean-square-error (RMSE) being 12% of the average yield and 50% of the standard deviation for the validation dataset using predicted weather data. With perfect weather data, the RMSE would be reduced to 11% of the average yield and 46% of the standard deviation. We also performed feature selection based on the trained DNN model, which successfully decreased the dimension of the input space without significant drop in the prediction accuracy. Our computational results suggested that this model significantly outperformed other popular methods such as Lasso, shallow neural networks (SNN), and regression tree (RT). The results also revealed that environmental factors had a greater effect on the crop yield than genotype.
Hybrid Machine Learning Models for Crop Yield Prediction
School of the built Environment（建筑环境学院）；Alba Regia Technical Faculty（阿尔巴雷吉亚技术学院）；Oxford Brookes University（牛津布鲁克斯大学）；Obuda University（欧布达大学）；University of Pannonia（潘诺尼亚大学）；J. Selye University（塞耶大学）；Bauhaus Universität Weimar（魏玛包豪斯大学）
Predicting Crop Yield With Machine Learning: An Extensive Analysis Of Input Modalities And Models On a Field and sub-field Level
University of Kaiserslautern-Landau (RPTU)（凯泽斯劳滕-兰道大学）；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心）；Vision Impulse GmbH（Vision Impulse 有限责任公司）
Explainability of Sub-Field Level Crop Yield Prediction using Remote Sensing
RPTU Kaiserslautern-Landau and the German Research Center for Artificial Intelligence (DFKI)（莱茵-威斯巴登大学（RPTU）凯撒斯劳滕-兰道分校和德国人工智能研究中心（DFKI））；German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））；Forschungszentrum Jülich GmbH（julich研究中心）；University of Bonn（波恩大学）
Informed Learning for Estimating Drought Stress at Fine-Scale Resolution Enables Accurate Yield Prediction
German Research Center for Artificial Intelligence（德国人工智能研究中心）；Department of Computer Science, University of Kaiserslautern-Landau（科隆-兰道大学计算机科学系）；Bernoulli Institute, University of Groningen（格罗宁根大学伯努利学院）
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）
Can Machine Learning Forecast Rice Yields in Data-Constrained Settings? Satellite Climate Data, National Crop Statistics, and Lessons from Sierra Leone
Seidenberg School of Computer Science & Information Systems Pace University, New York, USA（佩斯大学塞登伯格计算机科学与信息系统学院，纽约，美国）；RiseAfrica Foundation for STEM and Innovation Sierra Leone, West Africa（RiseAfrica STEM与创新基金会，塞拉利昂，西非）
Federated Learning Architectures: A Performance Evaluation with Crop Yield Prediction Application
Department of Computer Science Mahishadal Raj College, Mahishadal, West Bengal, 721628, India；Distributed Systems (CLOUDS) Laboratory, \ of Computing；Information Systems, The University of Melbourne, Victoria, 3052, Australia
A Comparative Study of Deep Reinforcement Learning for Crop Production Management
University of Texas at Arlington（德克萨斯大学阿灵顿分校）；Mississippi State University（密西西比州立大学）；USDA-ARS Genetics and Sustainable Agriculture Research Unit（美国农业部农业研究局遗传与可持续农业研究单元）
Productive Crop Field Detection: A New Dataset and Deep Learning Benchmark Results
Federal University of São Carlos（圣卡洛斯联邦大学）；John Deere（约翰迪尔）
在精准农业中，检测高产农田是一项必不可少的实践，使农民能够单独评估操作性能，并比较不同的种子品种，农药和肥料。然而，手动识别生产领域往往是一项耗时且容易出错的任务。以前的研究探索了使用先进的机器学习算法检测农田的不同方法，但它们通常缺乏高质量的标记数据。在这种情况下，我们提出了一个高质量的数据集，该数据集由机器操作生成，并与随时间推移跟踪的Sentinel-2图像相结合。据我们所知，这是第一个使用该技术来克服缺乏标记样本的问题。接下来，我们应用未标记数据的半监督分类和最先进的监督和自监督深度学习方法来自动检测高产农田。最后，结果证明了正未标记学习的高准确性，这完全符合我们对正样本具有高置信度的问题。考虑到存在精确的数据集和对比学习（考虑到我们没有全面的标记数据集可用的情况），在Triplet Loss Siamese中发现了最佳性能。
Transferring learned patterns from ground-based field imagery to predict UAV-based imagery for crop and weed semantic segmentation in precision crop farming
University of Lincoln（林肯大学）；Flanders Make（法兰德斯制造研究院）；Ghent University（根特大学）；Flanders Research Institute for Agriculture, Fisheries and Food (ILVO)（法兰德斯农业、渔业与食品研究所）；Swedish University of Agricultural Sciences（瑞典农业科学大学）
杂草和作物分割正成为利用当前计算机视觉和深度学习技术的精准农业日益不可或缺的一部分。已经基于用来自各种平台的相机捕获的图像进行了广泛的研究。无人机（UAV）和包括农业机器人在内的地面车辆是田间数据汇集的两种流行平台。它们都有助于特定地点的杂草管理（SSWM），以保持作物产量。目前，来自这两个平台的数据是分开处理的，尽管共享相同的语义对象（weed和crop）。在我们的论文中，我们开发了一个深度卷积网络，可以预测来自无人机的田间和空中图像，用于杂草分割和映射，仅在训练阶段提供田间图像。网络学习过程通过浅层和深层的特征图可视化。结果表明，该模型对农田数据集农作物（玉米）、杂草和土壤背景分割的平均交集（IOU）值分别为0.744，0.577，0.979，与采用相同模型的无人机航拍图像的分割性能相比，农作物（玉米）、杂草和土壤背景的IOU值分别为0.744，0.577，0.979，杂草和土壤背景值分别为0.596、0.407和0.875。为了估计对使用植物保护剂的影响，我们根据预测的杂草地图量化除草剂喷洒节省率和网格大小（喷洒分辨率）之间的关系。当喷雾分辨率为1.78 × 1.78 cm ~ 2时，喷雾节省率可达90%。研究表明，所开发的深度卷积神经网络可用于田间和航空图像中的杂草分类，并取得了令人满意的结果。
