Banana Fusarium Wilt Disease Detection by Supervised and Unsupervised Methods from UAV-Based Multispectral Imagery

Abstract

Banana Fusarium wilt (BFW) is a devastating disease with no effective cure methods. Timely and effective detection of the disease and evaluation of its spreading trend will help farmers in making right decisions on plantation management. The main purpose of this study was to find the spectral features of the BFW-infected canopy and build the optimal BFW classification models for different stages of infection. A RedEdge-MX camera mounted on an unmanned aerial vehicle (UAV) was used to collect multispectral images of a banana plantation infected with BFW in July and August 2020. Three types of spectral features were used as the inputs of classification models, including three-visible-band images, five-multispectral-band images, and vegetation indices (VIs). Four supervised methods including Support Vector Machine (SVM), Random Forest (RF), Back Propagation Neural Networks (BPNN) and Logistic Regression (LR), and two unsupervised methods including Hotspot Analysis (HA) and Iterative Self-Organizing Data Analysis Technique Algorithm (ISODATA) were adopted to detect the BFW-infected canopies. Comparing to the healthy canopies, the BFW-infected canopies had higher reflectance in the visible region, but lower reflectance in the NIR region. The classification results showed that most of the supervised and unsupervised methods reached excellent accuracies. Among all the supervised methods, RF based on the five-multispectral-band was considered as the optimal model, with higher overall accuracy (OA) of 97.28% and faster running time of 22 min. For the unsupervised methods, HA reached high and balanced OAs of more than 95% based on the selected VIs derived from the red and NIR band, especially for WDRVI, NDVI, and TDVI. By comprehensively evaluating the classification results of different metrics, the unsupervised method HA was recommended for BFW recognition, especially in the late stage of infection; the supervised method RF was recommended in the early stage of infection to reach a slightly higher accuracy. The results found in this study could give advice for banana plantation management and provide approaches for plant disease detection.

The Advance of Fusarium Wilt Tropical Race 4 in Musaceae of Latin America and the Caribbean: Current Situation

“…The bibliometric analysis of the scientific production of Foc TR4 in LAC shows that there is a growing interest in this topic. The number of publications on TR4 has increased in recent years, indicating that researchers in the region are actively working on finding solutions to this problem with innovative techniques based on artificial intelligence [ 39 , 40 ], aerial images [ 18 , 41 ], and machine learning methods [ 42 , 43 , 44 ].…”

“…In all the cases reported to date, once a plantation has been infected, the management of Foc TR4 has been extremely difficult and costly [ 16 , 17 ]. The impact of TR4 on the banana industry in LAC is significant [ 10 , 11 , 12 , 18 ]. The fungus has caused significant losses in productivity and profitability for banana growers in the region, which could hurt the livelihoods of small-scale farmers and the overall economy of the countries where banana is a major crop [ 19 ].…”

“…The first reports of Foc TR4 in Colombia and Peru were in 2019 and 2021, respectively, and in the case of Venezuela, the recent declaration was issued in early 2023. Since then, the fungus has spread rapidly in these countries, causing significant losses in productivity and profitability for banana growers in the region [ 12 , 18 ]. The fungus has had a particularly severe impact on small-scale farmers, who are heavily dependent on banana production for their livelihoods [ 13 ].…”

Evaluation of Diverse Convolutional Neural Networks and Training Strategies for Wheat Leaf Disease Identification with Field-Acquired Photographs

“…In addition to RGB cameras, more-informative sensors (e.g., multispectral or hyperspectral sensors) can be effectively used for image acquisition of crop disease [4,43,44]. Generally, multi-and hyperspectral sensors are mounted on unmanned aerial vehicle (UAV) and can obtain more spectral information of crop disease and cover larger areas than can be accomplished with proximal measurement [45,46]. Therefore, it is worth further exploring the performance and potential of CNNs and different training strategies on crop disease diagnosis.…”

Statistical Analysis between Soil Properties and Fusarium Wilt Disease in Banana

“…The most prevalent Foc is Tropical Race 4 (TR4), which threatens a wide Musa spp [2]. Diseased banana typically encounters wilting and yellowing leaves resulting from blocked xylem and no water transportation [3][4]. The Foc enters the vascular tissues and rapidly produces a high volume of chlamydospores, microconidia, and macroconidia across the entire banana plant [5].…”