Smart Big Data in Precision Agricultural Applications: Acquisition, Advanced Analytics, and Plant Physiology-informed Machine Learning

Big data acquisition platforms, such as small unmanned aerial vehicles (UAVs), unmanned ground vehicles (UGVs), and proximate sensors for precision agriculture, especially for heterogeneous crops, such as vineyards and orchards, are gaining interest from both researchers and growers. For example, lightweight sensors mounted on UAVs, such as multispectral and thermal infrared cameras, can be used to collect high-resolution images. The higher temporal and spatial resolutions of the images, relatively low operational costs, and nearly real-time image acquisition make the UAVs an ideal platform for mapping and monitoring the variability of crops over large acreage. The data acquisition platforms and analytics can create big data and demand fractional-order thinking due to the “complexity” and, thus, variability inherent in the process. Much hope is placed on machine learning (ML). How can an ML model learn from big data efficiently (optimally) and make the big data “smart” is important in agricultural research? The key to the learning process is the plant physiology and optimization method. Designing an efficient optimization method poses three questions: 1.) What is the best way to optimize? 2.) What is the more optimal way to optimize? 3.) Can we demand “more optimal machine learning,” for example, deep learning with the minimum or smallest labeled data for agriculture? Therefore, in this dissertation, the author investigated the foundations of the plant physiology-informed machine learning (PPIML) and the principle of tail matching (POTM) framework. He elucidated their role in modeling, analyzing, designing, and managing complex systems based on the big data in precision agriculture. Plant physiology entails the complexity of growth. The complex system has both deterministic and stochastic dynamic processes with external driving processes characterized and modeled using fractional calculus-based models, which will better inform the complexity-informed machine learning (CIML) algorithms. Data acquisition platforms, such as low-cost UAVs, UGVs, and edge-AI sensors, were designed and built to demonstrate their reliability and robustness for remote and proximate sensing in agricultural applications. Research results showed that the PPIML, POTM, CIML, and the data acquisition platforms were reliable, robust, and smart tools for precision agricultural research in varying situations, such as water stress detection, early detection of nematodes, yield estimation, and evapotranspiration (ET) estimation. The application of these tools has the potential to assist stakeholders in their crop management decisions