Various methods and specialized software programs are available for processing two-dimensional gel electrophoresis (2-DGE) images. However, due to the anomalies present in these images, a reliable, automated, and highly reproducible system for 2-DGE image analysis has still not been achieved. The most common anomalies found in 2-DGE images include vertical and horizontal streaking, fuzzy spots, and background noise, which greatly complicate computational analysis. In this paper, we review the preprocessing techniques applied to 2-DGE images for noise reduction, intensity normalization, and background correction. We also present a quantitative comparison of non-linear filtering techniques applied to synthetic gel images, through analyzing the performance of the filters under specific conditions. Synthetic proteins were modeled into a two-dimensional Gaussian distribution with adjustable parameters for changing the size, intensity, and degradation. Three types of noise were added to the images: Gaussian, Rayleigh, and exponential, with signal-to-noise ratios (SNRs) ranging 8–20 decibels (dB). We compared the performance of wavelet, contourlet, total variation (TV), and wavelet-total variation (WTTV) techniques using parameters SNR and spot efficiency. In terms of spot efficiency, contourlet and TV were more sensitive to noise than wavelet and WTTV. Wavelet worked the best for images with SNR ranging 10–20 dB, whereas WTTV performed better with high noise levels. Wavelet also presented the best performance with any level of Gaussian noise and low levels (20–14 dB) of Rayleigh and exponential noise in terms of SNR. Finally, the performance of the non-linear filtering techniques was evaluated using a real 2-DGE image with previously identified proteins marked. Wavelet achieved the best detection rate for the real image.

The avocado cv. Hass requires a suitable rootstock for optimal development under water stress. This study evaluated the performance of two avocado rootstocks (ANRR88 and ANGI52) grafted onto cv. Hass under four water stress conditions, 50% and 25% deficit, and 50% and 25% excess during the nursery stage. Plant height, leaf area (LA), dry matter (DM), and Carbon (OC) content in the roots, stems, and leaves were measured. Root traits were evaluated using digital imaging, and three vegetation indices (NDVI, CI_RE, and MTCI) were used to quantify stress. The results showed that genotype significantly influenced the response to water stress. ANRR88 exhibited adaptation to moderate to high water deficits. ANGI52 adapted better to both water deficit and excess, and showed greater root exploration. LA and DM reductions of up to 60% were observed in ANRR88, suggesting a higher sensitivity to extreme changes in water availability. More than 90% of the total OC accumulation was observed in the stem and roots. The NDVI and the MTCI quantified the presence and levels of stress applied, and the 720 nm band provided high precision and speed for detecting stress. These insights are crucial for selecting rootstocks that ensure optimal performance under varying water availability, enhancing productivity and sustainability.

Abiotic stress factors can be detected using visible and near-infrared spectral signatures. Previous work demonstrated the potential of this technology in crop monitoring, although a large majority used vegetation indices, which did not consider the complete spectral information. This work explored the capabilities of spectral information for abiotic stress detection using supervised machine learning techniques such as support vector machine (SVM), random forest (RF), and neural network (NN). This study used avocados grown under various water treatments, maize submitted to nitrogen deficiency, and common beans under phosphorous restriction. The spectral characterization of the crops subjected to abiotic stress was studied on the visible to near-infrared (450 to 900 nm) spectrum, identifying discriminative bands and spectral ranges. Then, the advantages of using an integrated approach based on machine learning to detect abiotic stress in crops were demonstrated. Instead of relying on vegetation indices, the proposed approach used several spectral features obtained by analyzing the discriminative signature shape, applying a spectral subset band selection algorithm based on similarity, and using the minimum redundancy maximum relevance (MRMR), F-test and chi-square test ranks for feature selection. The results showed that supervised classifiers applied to the spectral features outperform the accuracies obtained from vegetation indices. The best common bean results were obtained using SVM with accuracies up to 91%; for maize and avocado, NN obtained 90% and 82%, respectively. It is noted that detection accuracy depends on various factors, such as crop type, genotype, and level of stress.