Introduction Verticillium wilt is a severe soil-borne disease that affects cotton growth and yield. Traditional monitoring methods, which rely on manual investigation, are inefficient and impractical for large-scale applications. This study introduces a novel approach combining machine learning with feature selection to identify sensitive spectral features for accurate and efficient detection of cotton Verticillium wilt.Methods We conducted comprehensive hyperspectral measurements using handheld devices (350-2500 nm) to analyze cotton leaves in a controlled greenhouse environment and employed Unmanned Aerial Vehicle (UAV) hyperspectral imaging (400-995 nm) to capture canopy-level data in field conditions. The hyperspectral data were pre-processed to extract wavelet coefficients and spectral indices (SIs), enabling the derivation of disease-specific spectral features (DSSFs) through advanced feature selection techniques. Using these DSSFs, we developed detection models to assess both the incidence and severity of leaf damage by Verticillium wilt at the leaf scale and the incidence at the canopy scale. Initial analysis identified critical spectral reflectance bands, wavelet coefficients, and SIs that exhibited dynamic responses as the disease progressed.Results Model validation demonstrated that the incidence detection models at the leaf scale achieved a peak classification accuracy of 85.83%, which is about 10% higher than traditional methods without feature selection. The severity detection models showed improved precision as disease severity of damage increased, with accuracy ranging from 46.82% to 93.10%. At the canopy scale, UAV-based hyperspectral data achieved a remarkable classification accuracy of 93.0% for disease incidence detection.Discussion This study highlights the significant impact of feature selection on enhancing the performance of hyperspectral-based remote sensing models for cotton wilt monitoring. It also explores the transferability of sensitive spectral features across different scales, laying the groundwork for future large-scale early warning systems and monitoring cotton Verticillium wilt.

Powdery Mildew Blumeria graminis (PMBG) is one of the most dangerous diseases for winter wheat plants, causing damage to all above-ground plant organs. The main aim of this study is to develop and validate machine learning (ML) models with explainable AI (XAI) capabilities for accurate risk prediction of PMBG in winter wheat crops at the pre-symptomatic stage. Multiple heterogeneous ML classifiers with XAI for PMBG risk prediction have been developed in this study. The weather data used in this study were collected from two regions in Ukraine and included hourly air temperature, solar radiation, leaf wetness duration and other measurements of soil and climatic parameters. Several different feature selection approaches were leveraged to retrieve the most salient features. The multistack of ML models has been used to find the best-performing pipeline, which achieved an accuracy of 82 %. Further, diverse XAI methods such as Shapley Additive Values (SHAP), ELI5, Anchor and Local Interpretable Model-agnostic Explanations (LIME) have been applied to understand the model predictions. The precision, recall, f1-score and AUC obtained were 85%, 82%, 82% and 72 % respectively. As a result a decision support system has been developed to predict the risk of wheat powdery mildew using soil and climatic parameters monitoring, ML, and XAI. This study provides the holistic risk prediction of PMBG for the enhancement of wheat stress resistance during the full cycle of its cultivation in open-field conditions.

Engineers often estimate the amount of liquefaction-induced building settlements (LIBS) as a performance proxy to assess the potential of earthquake-induced damage to buildings. The first robust LIBS models were initially developed in 2017 and 2018 using traditional statistical approaches. More recently, machine learning techniques have started to be used in developing LIBS models. These recent efforts are a step forward in realizing the potential of machine learning in liquefaction engineering; however, they have often considered only one ML technique for a given dataset and typically used only held-out test sets for model assessment. In this study, five ML-based LIBS models with varying flexibility (i.e., ridge regression, partial least square regression - PLSR, random forest, gradient boosting decision tree - GBDT, and support vector regression) are developed using a LIBS database generated by soil-structure numerical simulations of different buildings and soil profiles shaken by ground motions with varying intensity measures. The motivation for considering models with different flexibility is to include different bias-variance trade-offs. Feature selection with different ML techniques indicates that cumulative absolute velocity, spectral acceleration at one second, contact pressure, foundation width, the thickness of the liquefiable layer, and a shearing liquefaction index are important features in estimating LIBS. The developed ML-based models are assessed considering prediction accuracy in test sets, performance against centrifuge tests and case histories, and trends. The assessment indicates that the random forest, GBDT, and SVR models perform best, providing standard deviation reductions up to 40% relative to a multi-linear regression. Specifically, the random forest and GBDT models exhibit a root mean square error (RMSE) of 0.29 and a coefficient of determination (R2) of 0.93 on test sets, demonstrating a notable improvement compared to a traditional multi-linear regression model, which yields an RMSE of 0.47 and an R2 of 0.82. Moreover, random forest and GBDT, alongside SVR, show a good performance in centrifuge tests and case histories. Finally, given the scarcity of LIBS models, this study also contributes to treating epistemic uncertainties in estimating LIBS, which is ultimately beneficial for performance-based assessments.

Agriculture is considered the leading field around the world, which is also the backbone of India. Agriculture is in a flawed state because the temperature changes, along with their uncertainty, cause huge damage to the crops during the manufacturing process. So, the appropriate prediction of crop expansion plays a vital role in the management of crop growth. This prediction can enhance the federated industries to make their sustainability toward the occupation. Recently, the farmers have not selected suitable crops for their cultivation based on soil factors. This makes a negative impact on crop yield, and thus, the Indian farmers can suffer from severe losses besides the monetary front. Hence, the optimal crop recommendation model has to consider different parameters of the soil for forecasting the best crop for cultivation, which increases crop growth and crop production. Thus, this research work explores a new crop recommendation model for precision agriculture intending to promote crop yield and alleviate the loss to farmers. Initially, this research work gathers the standard data regarding the agricultural parameters of some areas. Then, the deep features using an autoencoder, and statistical features are gathered along with the Principal Component Analysis (PCA)-based features. Next, all three sets of features are fused and fed to the developed Adaptive Henry Gas Solubility Optimization (AHGSO) for selecting the optimal features. Finally, the chosen optimal features are fed to the recommendation stage, where a Gated Recurrent Unit with Ridge Classifier (GRU-RC) is suggested for getting the precise outcome regarding the recommended crop suitable to that agricultural parameter. Here, the optimal solutions are attained by tuning the parameters of GRU and ridge classifier with the same I-HGSO. At last, the results obtained from the hybrid method can be considered more efficient.