Precision agriculture is a rapidly developing field aimed at addressing current concerns about agricultural sustainability. Machine learning is the cutting edge technology underpinning precision agriculture, enabling the development of advanced disease detection and classification methods. This paper presents a review of the application of machine learning and deep learning techniques in precision agriculture, specifically for detecting and classifying plant diseases. We propose a novel classification scheme that categorizes all relevant works in the associated classes. We separate the studies into two main categories depending on the methodology that they use (i.e., classification or object detection). In addition, we present the available datasets for plant disease detection and classification. Finally, we perform an extensive computational study on five state-of-the-art object detection algorithms on PlantDoc dataset to detect diseases present on the leaves, and eighteen state-of-the-art classification algorithms on PlantDoc dataset to predict whether or not there is a disease in a leaf. Computational results show that object detection accuracy is high with YOLOv5. For the image classification task, the networks ResNet50 and MobileNetv2 have the most optimal trade-off on accuracy and training time.

Optimization solvers include many options that allow users to control algorithmic aspects that may have a considerable impact on solver performance. Tuning solver options is often necessary to reduce execution time and improve solution quality. Previous studies of solver tuning techniques have focused on mixed-integer linear programming and local nonlinear programming solvers. In this paper, we investigate the potential of tuning a global optimization solver for nonlinear and mixed-integer nonlinear programming problems. In particular, derivative-free optimization (DFO) algorithms are used to find optimal values for options of the global optimization solver BARON. A set of 126 problems from the GLOBALLib and MINLPLib collections are utilized in a computational study from which we conclude that tuning options can improve the default performance of BARON for individual problems and an entire library. Additionally, we present a systematic comparison of 27 DFO solvers in terms of their ability to improve the performance of the global solver. We find that several DFO implementations are much better than others in terms of finding optimal tuning parameters.