Useful AI applications in agriculture: aggregation of machine learning techniques for weather forecasting and banana plant counting

Modern problems in agricultural seek methods to increase the convenience, reliability accuracy and at the same time, cost efficacy in precision farming. To exploit the global research gaps in sustainable agriculture, this thesis organizes three different works committed to provide solutions to three modern agricultural problems: reliable crop modeling, accurate crop counting and cost-effective crop health monitoring. As strategic solutions, this study proposes the use of emerging advancements on recent artificial intelligence technologies, weather forecasting, web-services, aerial imagery and digital image processing to connect the crucial cores of sustainable agriculture visions. The outputs of this work is targeted help decision makers, and specially the farmers themselves, to increase the productivity of farms for better yield, and to draw young people to the farms to meet the global hunger of 21st century with sustainability in life support and food security. The unavailability of seasonal weather data at the simulation time (often beginning of a growth season) forces decision makers in crop growth assessment to consider multiple weather scenarios, which are often generated from longtime observed data. Ironically these scenario immediately become “outdated” as soon as the season begins, because they are always different from newly observed data. In the first research of this thesis, we investigate this dilemma and in particular address three questions: determination of most successful scenario, classification of scenarios into fresh and stale, and generation of a new scenario from fresh scenarios. Algorithms to solve these questions are given as strategies for prediction games of weather generators. We also elaborate on the applications of our results in networking existing weather generation web services.The production of banana - one of the highly consumed fruits - is highly affected due to loss of certain number of banana plants in an early phase of vegetation. This affects the ability of farmers to forecast and estimate the production of banana. In the second research of this thesis, we propose a deep learning based algorithm for detection and counting of banana plants, using high resolution RGB aerial images collected from Unmanned Aerial Vehicle (UAV). An attempt to detect the plants on the normal RGB images resulted only 72.8% recall for our sample images of a commercial farm in Thailand. To improve this result, we use several image processing methods to enhance the vegetative properties - radiance, hue, saturation and values (HSV), and chlorophyll content of banana leaves - to generate multiple variants of aerial images. Then we separately train a parameter-optimized Convolutional Neural Network (CNN) on manually interpreted banana plant samples, to produce multiple results of detection. We apply the same algorithm on images collected from multiple flying altitudes, and merge the detection results to increase the recall to 97.6%.Unmanned Aerial Vehicle (UAV) photogrammetry has allowed to monitor crop growth/health and remotely estimate biomass through calculation of Vegetation Indices (VI). However, some of the indices require costly sensors, and the process of generating VI maps from UAV images also requires commercial off-the-shelf software packages. The third research of this thesis uses existing open-source tools and methods to develop an algorithm for a web-service that can create orthophotos, canopy height model and VI's for red-green-blue (RGB) images collected from UAV. We also discuss on ways to balance between the processing speed and quality of outputs, and further compare them to the outputs of an existing state-of-the-art commercial service.现代农业领域的核心难题之一，是在精准农业中寻求兼顾便捷性、可靠性与准确性，同时提升成本效益的解决方案。为填补可持续农业领域的全球研究空白，本论文开展三项独立研究，分别针对三大现代农业痛点展开解决方案探索：可靠的作物建模、精准的作物计数，以及高性价比的作物健康监测。作为核心策略方案，本研究依托当前人工智能技术、天气预报、Web服务、航空影像与数字图像处理等领域的新兴进展，打通可持续农业愿景的关键核心环节。本研究的成果旨在辅助决策者，尤其是广大农户，提升农场生产效率与作物产量，同时吸引青年群体投身农业，以可持续的生命保障与粮食安全路径应对21世纪全球粮食危机。在作物生长模拟阶段（通常为生长季初期），季节性气象数据的缺失迫使作物生长评估决策者依赖基于长期观测数据生成的多套气象情景方案。但讽刺的是，一旦生长季启动，这些预设情景便会因与实时观测数据不符而迅速“过时”。针对这一困境，本论文第一项研究展开针对性探索，重点解决三大核心问题：最优情景的判定、情景的新鲜/陈旧分类，以及基于新鲜情景生成新的适配方案。本研究提出用于气象发生器预测博弈的算法作为解决方案，并详细阐述了研究成果在现有气象生成Web服务组网中的应用路径。作为全球高消费量水果之一，香蕉的产量极易因植被早期阶段的植株损失受到严重影响，进而干扰农户的产量预测与估算工作。针对该问题，本论文第二项研究提出一种基于深度学习的香蕉植株检测与计数算法，所用数据为无人机（Unmanned Aerial Vehicle, UAV）采集的高分辨率RGB航空影像。初始阶段仅使用普通RGB影像进行植株检测时，针对泰国某商业农场的样本图像仅能达到72.8%的召回率。为提升检测性能，本研究通过多种图像处理手段强化植被特征——包括香蕉叶片的辐射度、色调、饱和度与明度（HSV）以及叶绿素含量，从而生成多组航空影像变体。随后基于人工标注的香蕉植株样本，单独训练参数优化后的卷积神经网络（Convolutional Neural Network, CNN），得到多组检测结果。本研究将同一算法应用于不同飞行高度采集的影像，并融合多组检测结果，最终将召回率提升至97.6%。无人机摄影测量技术可通过植被指数（Vegetation Indices, VI）计算实现作物生长/健康状况监测与生物量遥感估算，但部分植被指数需要使用昂贵的专业传感器，且从无人机影像生成植被指数地图的流程也依赖商用现成软件包。本论文第三项研究依托现有开源工具与方法，开发一款Web服务算法，可基于无人机采集的RGB影像生成正射影像、冠层高度模型与植被指数。本研究同时探讨了处理速度与输出质量之间的平衡策略，并将该算法的输出结果与现有主流商用服务的输出进行了对比分析。