In recent years, remote sensing researchers have investigated the use of different modalities (or combinations of modalities) for classification tasks. Such modalities can be extracted via a diverse range of sensors and images. Currently, there are no (or only a few) studies that have been done to increase the land cover classification accuracy via unmanned aerial vehicle (UAV)–digital surface model (DSM) fused datasets. Therefore, this study looks at improving the accuracy of these datasets by exploiting convolutional neural networks (CNNs). In this work, we focus on the fusion of DSM and UAV images for land use/land cover mapping via classification into seven classes: bare land, buildings, dense vegetation/trees, grassland, paved roads, shadows, and water bodies. Specifically, we investigated the effectiveness of the two datasets with the aim of inspecting whether the fused DSM yields remarkable outcomes for land cover classification. The datasets were: (i) only orthomosaic image data (Red, Green and Blue channel data), and (ii) a fusion of the orthomosaic image and DSM data, where the final classification was performed using a CNN. CNN, as a classification method, is promising due to hierarchical learning structure, regulating and weight sharing with respect to training data, generalization, optimization and parameters reduction, automatic feature extraction and robust discrimination ability with high performance. The experimental results show that a CNN trained on the fused dataset obtains better results with Kappa index of ~0.98, an average accuracy of 0.97 and final overall accuracy of 0.98. Comparing accuracies between the CNN with DSM result and the CNN without DSM result for the overall accuracy, average accuracy and Kappa index revealed an improvement of 1.2%, 1.8% and 1.5%, respectively. Accordingly, adding the heights of features such as buildings and trees improved the differentiation between vegetation specifically where plants were dense.

This study predicts forest fire susceptibility in Chaloos Rood watershed in Iran using three machine learning (ML) models—multivariate adaptive regression splines (MARS), support vector machine (SVM), and boosted regression tree (BRT). The study utilizes 14 set of fire predictors derived from vegetation indices, climatic variables, environmental factors, and topographical features. To assess the suitability of the models and estimating the variance and bias of estimation, the training dataset obtained from the Natural Resources Directorate of Mazandaran province was subjected to resampling using cross validation (CV), bootstrap, and optimism bootstrap techniques. Using variance inflation factor (VIF), weight indicating the strength of the spatial relationship of the predictors to fire occurrence was assigned to each contributing variable. Subsequently, the models were trained and validated using the receiver operating characteristics (ROC) area under the curve (AUC) curve. Results of the model validation based on the resampling techniques (non, 5- and 10-fold CV, bootstrap and optimism bootstrap) produced AUC values of 0.78, 0.88, 0.90, 0.86 and 0.83 for the MARS model; 0.82, 0.82, 0.89, 0.87, 0.84 for the SVM and 0.87, 0.90, 0.90, 0.90, 0.91 for the BRT model. Across the individual model, the 10-fold CV performed best in MARS and SVM with AUC values of 0.90 and 0.89. Overall, the BRT outperformed the other models in all ramification with highest AUC value of 0.91 using optimism bootstrap resampling algorithm. Generally, the resampling process enhanced the prediction performance of all the models.

Predicting landslide occurrences can be difficult. However, failure to do so can be catastrophic, causing unwanted tragedies such as property damage, community displacement, and human casualties. Research into landslide susceptibility mapping (LSM) attempts to alleviate such catastrophes through the identification of landslide prone areas. Computational modelling techniques have been successful in related disaster scenarios, which motivate this work to explore such modelling for LSM. In this research, the potential of supervised machine learning and ensemble learning is investigated. Firstly, the Flexible Discriminant Analysis (FDA) supervised learning algorithm is trained for LSM and compared against other algorithms that have been widely used for the same purpose, namely Generalized Logistic Models (GLM), Boosted Regression Trees (BRT or GBM), and Random Forest (RF). Next, an ensemble model consisting of all four algorithms is implemented to examine possible performance improvements. The dataset used to train and test all the algorithms consists of a landslide inventory map of 227 landslide locations. From these sources, 13 conditioning factors are extracted to be used in the models. Experimental evaluations are made based on True Skill Statistic (TSS), the Receiver Operation characteristic (ROC) curve and kappa index. The results show that the best TSS (0.6986), ROC (0.904) and kappa (0.6915) were obtained by the ensemble model. FDA on its own seems effective at modelling landslide susceptibility from multiple data sources, with performance comparable to GLM. However, it slightly underperforms when compared to GBM (BRT) and RF. RF seems most capable compared to GBM, GLM, and FDA, when dealing with all conditioning factors.

Assessment of the most appropriate groundwater conditioning factors (GCFs) is essential when performing analyses for groundwater potential mapping. For this reason, in this work, we look at three statistical factor analysis methods—Variance Inflation Factor (VIF), Chi-Square Factor Optimization, and Gini Importance—to measure the significance of GCFs. From a total of 15 frequently used GCFs, 11 most effective ones (i.e., altitude, slope angle, plan curvature, profile curvature, topographic wetness index, distance from river, distance from fault, river density, fault density, land use, and lithology) were finally selected. In addition, 917 spring locations were identified and used to train and test three machine learning algorithms, namely Mixture Discriminant Analysis (MDA), Linear Discriminant Analysis (LDA) and Random Forest (RF). The resultant trained models were then applied for groundwater potential prediction and mapping in the Haraz basin of Mazandaran province, Iran. MDA has been successfully applied for soil erosion and landslide mapping, but has not yet been fully explored for groundwater potential mapping (GPM). Although other discriminant methods, such as LDA, exist, MDA is worth exploring due to its capability to model multivariate nonlinear relationships between variables; it also undertakes a mixture of unobserved subclasses with regularization of non-linear decision boundaries, which could potentially provide more accurate classification. For the validation, areas under Receiver Operating Characteristics (ROC) curves (AUC) were calculated for the three algorithms. RF performed better with AUC value of 84.4%, while MDA and LDA yielded 75.2% and 74.9%, respectively. Although MDA performance is lower than RF, the result is satisfactory, because it is within the acceptable standard of environmental modeling. The outcome of factor analysis and groundwater maps emphasizes on optimization of multicolinearity factors for faster spatial modeling and provides valuable information for government agencies and private sectors to effectively manage groundwater in the region.

Large damages and losses resulting from floods are widely reported across the globe. Thus, the identification of the flood-prone zones on a flood susceptibility map is very essential. To do so, 13 conditioning factors influencing the flood occurrence in Brisbane river catchment in Australia (i.e., topographic, water-related, geological, and land use factors) were acquired for further processing and modeling. In this study, artificial neural networks (ANN), deep learning neural networks (DLNN), and optimized DLNN using particle swarm optimization (PSO) were exploited to predict and estimate the susceptible areas to the future floods. The significance of the conditioning factors analysis for the region highlighted that altitude, distance from river, sediment transport index (STI), and slope played the most important roles, whereas stream power index (SPI) did not contribute to the hazardous situation. The performance of the models was evaluated against the statistical tests such as sensitivity, specificity, the area under curve (AUC), and true skill statistic (TSS). DLNN and PSO-DLNN models obtained the highest values of sensitivity (0.99) for the training stage to compare with ANN. Moreover, the validations of specificity and TSS for PSO-DLNN recorded the highest values of 0.98 and 0.90, respectively, compared with those obtained by ANN and DLNN. The best accuracies by AUC were evaluated in PSO-DLNN (0.99 in training and 0.98 in testing datasets), followed by DLNN and ANN. Therefore, the optimized PSO-DLNN proved its robustness to compare with other methods.

In recent years, remote-sensing (RS) technologies have been used together with image processing and traditional techniques in various disaster-related works. Among these is detecting building damage from orthophoto imagery that was inflicted by earthquakes. Automatic and visual techniques are considered as typical methods to produce building damage maps using RS images. The visual technique, however, is time-consuming due to manual sampling. The automatic method is able to detect the damaged building by extracting the defect features. However, various design methods and widely changing real-world conditions, such as shadow and light changes, cause challenges to the extensive appointing of automatic methods. As a potential solution for such challenges, this research proposes the adaption of deep learning (DL), specifically convolutional neural networks (CNN), which has a high ability to learn features automatically, to identify damaged buildings from pre- and post-event RS imageries. Since RS data revolves around imagery, CNNs can arguably be most effective at automatically discovering relevant features, avoiding the need for feature engineering based on expert knowledge. In this work, we focus on RS imageries from orthophoto imageries for damaged-building detection, specifically for (i) background, (ii) no damage, (iii) minor damage, and (iv) debris classifications. The gist is to uncover the CNN architecture that will work best for this purpose. To this end, three CNN models, namely the twin model, fusion model, and composite model, are applied to the pre- and post-orthophoto imageries collected from the 2016 Kumamoto earthquake, Japan. The robustness of the models was evaluated using four evaluation metrics, namely overall accuracy (OA), producer accuracy ($\mathrm{PA}$), user accuracy ($\mathrm{UA}$), and F1 score. According to the obtained results, the twin model achieved higher accuracy (OA = 76.86%; F1 score = 0.761) compare to the fusion model (OA = 72.27%; F1 score = 0.714) and composite (OA = 69.24%; F1 score = 0.682) models.