A novel optimized repeatedly random undersampling for selecting negative samples: A case study in an SVM-based forest fire susceptibility assessment

Mechanism-Data Collaboration for Characterizing Sea Clutter Properties and Training Sample Selection

Multi-feature-based maritime radar target detection algorithms often rely on statistical models to accurately characterize sea clutter variations. However, it is a big challenge for these models to accurately characterize sea clutter due to the complexity of the marine environment. Moreover, the distribution of training samples captured from dynamic observation conditions is imbalanced. These multi-features extracted from inaccurate models and imbalanced data lead to overfitting or underfitting and degrade detection performance. To tackle these challenges, this paper proposes a mechanism-data collaborative method using the scattering coefficient as a representative feature. By establishing a mapping relationship between measured data and empirical values, the classical model is piecewise fitted to the measured data. A fusion strategy is then used to compensate for interval discontinuities, enabling accurate characterization of clutter properties in the current maritime environment. Based on the characterized clutter properties, a hybrid feature selection strategy is further proposed to construct a diverse and compact training sample set by integrating global density distribution with local gradient variation. The experiments based on field data are included to evaluate the effectiveness of the proposed method including sea clutter characterization accuracy and training sample selection across various scenarios. Experimental results demonstrate that the proposed method provides a more accurate representation of sea clutter characteristics. Moreover, the detectors trained with the proposed training samples exhibit strong generalization capability across diverse maritime environments under the condition of identical features and classifiers. These achievements highlight the importance of accurate sea clutter modeling and optimal training sample selection in improving target detection performance and ensuring the reliability of radar-based maritime surveillance.

Forest fire susceptibility assessment under small sample scenario: A semi-supervised learning approach using transductive support vector machine

Forest fires threaten global ecosystems, socio-economic structures, and public safety. Accurately assessing forest fire susceptibility is critical for effective environmental management. Supervised learning methods dominate this assessment, relying on a substantial dataset of forest fire occurrences for model training. However, obtaining precise forest fire location data remains challenging. To address this issue, semi-supervised learning emerges as a viable solution, leveraging both a limited set of collected samples and unlabeled data containing environmental factors for training. Our study employed the transductive support vector machine (TSVM), a key semi-supervised learning method, to assess forest fire susceptibility in scenarios with limited samples. We conducted a comparative analysis, evaluating its performance against widely used supervised learning methods. The assessment area for forest fire susceptibility lies in Dayu County, Jiangxi Province, China, renowned for its vast forest cover and frequent fire incidents. We analyzed and generated maps depicting forest fire susceptibility, evaluating prediction accuracies for both supervised and semi-supervised learning methods across various small sample scenarios (e.g., 4, 8, 12, 16, 20, 24, 28, and 32 samples). Our findings indicate that TSVM exhibits superior prediction accuracy compared to supervised learning with limited samples, yielding more plausible forest fire susceptibility maps. For instance, at sample sizes of 4, 16, and 28, TSVM achieves prediction accuracies of approximately 0.8037, 0.9257, and 0.9583, respectively. In contrast, random forests, the top performers in supervised learning, demonstrate accuracies of approximately 0.7424, 0.8916, and 0.9431, respectively, for the same small sample sizes. Additionally, we discussed three key aspects: TSVM parameter configuration, the impact of unlabeled sample size, and performance within typical sample sizes. Our findings support semi-supervised learning as a promising approach compared to supervised learning for forest fire susceptibility assessment and mapping, particularly in scenarios with small sample sizes.

Improving the prediction of wildfire susceptibility on Hawai'i Island, Hawai'i, using explainable hybrid machine learning models

This study presents a comparative analysis of four Machine Learning (ML) models used to map wildfire susceptibility on Hawai'i Island, Hawai'i. Extreme Gradient Boosting (XGBoost) combined with three meta-heuristic algorithms - Whale Optimization (WOA), Black Widow Optimization (BWO), and Butterfly Optimization (BOA) - were employed to map areas susceptible to wildfire. To generate a wildfire inventory, 1408 wildfire points were identified within the study area from 2004 to 2022. The four ML models (XGBoost, WOA-XGBoost, BWO-XGBoost, and BOA-XGBoost) were run using 14 wildfire-conditioning factors categorized into four main groups: topographical, meteorological, vegetation, and anthropogenic. Six performance metrics - sensitivity, specificity, positive predictive values, negative predictive values, the Area Under the receiver operating characteristic Curve (AUC), and the average precision (AP) of Precision-Recall Curves (PRCs) - were used to compare the predictive performance of the ML models. The SHapley Additive exPlanations (SHAP) framework was also used to interpret the importance values of the 14 influential variables for the modeling of wildfire on Hawai'i Island using the four models. The results of the wildfire modeling indicated that all four models performed well, with the BWO-XGBoost model exhibiting a slightly higher prediction performance (AUC = 0.9269), followed by WOA-XGBoost (AUC = 0.9253), BOA-XGBoost (AUC = 0.9232), and XGBoost (AUC = 0.9164). SHAP analysis revealed that the distance from a road, annual temperature, and elevation were the most influential factors. The wildfire susceptibility maps generated in this study can be used by local authorities for wildfire management and fire suppression activity.

Dynamic Population on Bio-Inspired Algorithms Using Machine Learning for Global Optimization

In the optimization field, the ability to efficiently tackle complex and high-dimensional problems remains a persistent challenge. Metaheuristic algorithms, with a particular emphasis on their autonomous variants, are emerging as promising tools to overcome this challenge. The term "autonomous" refers to these variants' ability to dynamically adjust certain parameters based on their own outcomes, without external intervention. The objective is to leverage the advantages and characteristics of an unsupervised machine learning clustering technique to configure the population parameter with autonomous behavior, and emphasize how we incorporate the characteristics of search space clustering to enhance the intensification and diversification of the metaheuristic. This allows dynamic adjustments based on its own outcomes, whether by increasing or decreasing the population in response to the need for diversification or intensification of solutions. In this manner, it aims to imbue the metaheuristic with features for a broader search of solutions that can yield superior results. This study provides an in-depth examination of autonomous metaheuristic algorithms, including Autonomous Particle Swarm Optimization, Autonomous Cuckoo Search Algorithm, and Autonomous Bat Algorithm. We submit these algorithms to a thorough evaluation against their original counterparts using high-density functions from the well-known CEC LSGO benchmark suite. Quantitative results revealed performance enhancements in the autonomous versions, with Autonomous Particle Swarm Optimization consistently outperforming its peers in achieving optimal minimum values. Autonomous Cuckoo Search Algorithm and Autonomous Bat Algorithm also demonstrated noteworthy advancements over their traditional counterparts. A salient feature of these algorithms is the continuous nature of their population, which significantly bolsters their capability to navigate complex and high-dimensional search spaces. However, like all methodologies, there were challenges in ensuring consistent performance across all test scenarios. The intrinsic adaptability and autonomous decision making embedded within these algorithms herald a new era of optimization tools suited for complex real-world challenges. In sum, this research accentuates the potential of autonomous metaheuristics in the optimization arena, laying the groundwork for their expanded application across diverse challenges and domains. We recommend further explorations and adaptations of these autonomous algorithms to fully harness their potential.

Exploring effective ways to increase reliable positive samples for machine learning-based urban waterlogging susceptibility assessments

Machine learning (ML)-based urban waterlogging susceptibility studies suffer from class imbalance, as fewer positive samples are generally available than potential negative samples. Few studies have considered optimizing the results by improving the quality of training samples. To address this issue, we explored effective approaches to reliably increase the numbers of positive samples for such studies. The Synthetic Minority Over-Sampling Technique (SMOTE) and Optimized Seed Spread Algorithm (OSSA), representative of oversampling (synthesizing new samples based on the feature space) and physical (simulating potential inundated area based on the mechanisms of water flow) approaches, respectively, were employed to increase the number of positive samples. Waterlogging in Shenzhen was selected as a case study using eight selected spatial variables. An elaborate experiment was conducted to compare the quality of added samples based on the classifiers' performance and accuracy of waterlogging susceptibility maps (WSMs). The results indicated that (1) the performance of classifiers generated with SMOTE was worse than the original samples, while the use of OSSA improved the trained classifiers, and (2) the accuracy of WSMs was not improved with SMOTE but increased markedly with OSSA. These results may be driven by the diversity of information and features of the added samples. This study indicates the use of SMOTE fails to synthesize reliable samples when applied to waterlogging analysis in Shenzhen, whereas an effective solution for generating reliable positive samples is to use OSSA that simulates the potential submerged regions based on the mechanisms of disaster occurrence and spread.

Debris flow susceptibility assessment based on information value and machine learning coupling method: from the perspective of sustainable development

Accurately assessing the susceptibility of debris flow disasters is of great significance for reducing the cost of disaster prevention and mitigation, as well as disaster losses. Machine learning (ML) models have been widely used in the susceptibility assessment of debris flow disasters. However, these models often have randomness in the selection of non-disaster data, which can lead to redundant information and poor applicability and accuracy of susceptibility evaluation results. To address this issue, this paper focuses on debris flow disasters in Yongji County, Jilin Province, China; optimizes the sampling method of non-disaster datasets in machine learning susceptibility assessment; and proposes a susceptibility prediction model that couples information value (IV) with artificial neural network (ANN) and logistic regression (LR) models. A debris flow disaster susceptibility distribution map with higher accuracy was drawn based on this model. The model's performance is evaluated using the area under the receiver operating characteristic curve (AUC), information gain ratio (IGR), and typical disaster point verification methods. The results show that the rainfall and topography were found to be decisive factors in the occurrence of debris flow disasters, and the IV-ANN model established in this study had the highest accuracy (AUC = 0.968). Compared to traditional machine learning models, the coupling model produced an increase in economic benefit of about 25% while reducing the average disaster prevention and control investment cost by about 8%. Based on model's susceptibility map, this paper proposes practical disaster prevention and control suggestions that promote sustainable development in the region, such as establishing monitoring systems and information platforms to aid disaster management.

A modeling approach for estimating hydrogen sulfide solubility in fifteen different imidazole-based ionic liquids

Absorption has always been an attractive process for removing hydrogen sulfide (H₂S). Posing unique properties and promising removal capacity, ionic liquids (ILs) are potential media for H₂S capture. Engineering design of such absorption process needs accurate measurements or reliable estimation of the H₂S solubility in ILs. Since experimental measurements are time-consuming and expensive, this study utilizes machine learning methods to monitor H₂S solubility in fifteen various ILs accurately. Six robust machine learning methods, including adaptive neuro-fuzzy inference system, least-squares support vector machine (LS-SVM), radial basis function, cascade, multilayer perceptron, and generalized regression neural networks, are implemented/compared. A vast experimental databank comprising 792 datasets was utilized. Temperature, pressure, acentric factor, critical pressure, and critical temperature of investigated ILs are the affecting parameters of our models. Sensitivity and statistical error analysis were utilized to assess the performance and accuracy of the proposed models. The calculated solubility data and the derived models were validated using seven statistical criteria. The obtained results showed that the LS-SVM accurately predicts H₂S solubility in ILs and possesses R², RMSE, MSE, RRSE, RAE, MAE, and AARD of 0.99798, 0.01079, 0.00012, 6.35%, 4.35%, 0.0060, and 4.03, respectively. It was found that the H₂S solubility adversely relates to the temperature and directly depends on the pressure. Furthermore, the combination of OMIM⁺ and Tf₂N^-, i.e., [OMIM][Tf₂N] ionic liquid, is the best choice for H₂S capture among the investigated absorbents. The H₂S solubility in this ionic liquid can reach more than 0.8 in terms of mole fraction.

A Systematic Review of Applications of Machine Learning Techniques for Wildfire Management Decision Support

Wildfires threaten and kill people, destroy urban and rural property, degrade air quality, ravage forest ecosystems, and contribute to global warming. Wildfire management decision support models are thus important for avoiding or mitigating the effects of these events. In this context, this paper aims at providing a review of recent applications of machine learning methods for wildfire management decision support. The emphasis is on providing a summary of these applications with a classification according to the case study type, machine learning method, case study location, and performance metrics. The review considers documents published in the last four years, using a sample of 135 documents (review articles and research articles). It is concluded that the adoption of machine learning methods may contribute to enhancing support in different fire management phases.

An Optimized Weighted Naïve Bayes Method for Flood Risk Assessment

Floods occur frequently and cause considerable damage to local environments. Effectively assessing the flood risk contributes to reducing loss caused by such disasters. In this study, the weighted naïve Bayes (WNB) method was selected to evaluate flood risk, and the entropy weight method was employed to compute the weights. A sampling and verifying model was employed to generate the most accurate conditional probability table (MACPT) to calculate the probability of flooding. When using the framework integrating WNB with the sampling and verifying model, previous studies could not obtain a WNB-based MACPT and the WNB classification accuracy, for lacking WNB functions that could be called directly. Facing this issue, in this study we developed WNB functions with the MATLAB platform to directly integrate with the sampling and verifying model to generate a WNB-based MACPT, contributing to the greater interpretability and extensibility of the model. Shantou and Jieyang cities in China were selected as the study area. The results demonstrate that: (1) a WNB-based MACPT can reflect the real spatial distribution of flood risk and (2) the WNB outperform the NB when integrated with the sampling and verifying model. The resulting gridded estimation reveal a detailed spatial pattern of flood risk, which can serve as a realistic reference for decision making related to floods. Furthermore, the proposed method uses less data, which would be helpful in developing countries where long-term intensive hydrologic monitoring is limited.

A Collaborative Region Detection and Grading Framework for Forest Fire Smoke Using Weakly Supervised Fine Segmentation and Lightweight Faster-RCNN

Forest fires are serious disasters that affect countries all over the world. With the progress of image processing, numerous image-based surveillance systems for fires have been installed in forests. The rapid and accurate detection and grading of fire smoke can provide useful information, which helps humans to quickly control and reduce forest losses. Currently, convolutional neural networks (CNN) have yielded excellent performance in image recognition. Previous studies mostly paid attention to CNN-based image classification for fire detection. However, the research of CNN-based region detection and grading of fire is extremely scarce due to a challenging task which locates and segments fire regions using image-level annotations instead of inaccessible pixel-level labels. This paper presents a novel collaborative region detection and grading framework for fire smoke using a weakly supervised fine segmentation and a lightweight Faster R-CNN. The multi-task framework can simultaneously implement the early-stage alarm, region detection, classification, and grading of fire smoke. To provide an accurate segmentation on image-level, we propose the weakly supervised fine segmentation method, which consists of a segmentation network and a decision network. We aggregate image-level information, instead of expensive pixel-level labels, from all training images into the segmentation network, which simultaneously locates and segments fire smoke regions. To train the segmentation network using only image-level annotations, we propose a two-stage weakly supervised learning strategy, in which a novel weakly supervised loss is proposed to roughly detect the region of fire smoke, and a new region-refining segmentation algorithm is further used to accurately identify this region. The decision network incorporating a residual spatial attention module is utilized to predict the category of forest fire smoke. To reduce the complexity of the Faster R-CNN, we first introduced a knowledge distillation technique to compress the structure of this model. To grade forest fire smoke, we used a 3-input/1-output fuzzy system to evaluate the severity level. We evaluated the proposed approach using a developed fire smoke dataset, which included five different scenes varying by the fire smoke level. The proposed method exhibited competitive performance compared to state-of-the-art methods.

Few-shot pulse wave contour classification based on multi-scale feature extraction

The annotation procedure of pulse wave contour (PWC) is expensive and time-consuming, thereby hindering the formation of large-scale datasets to match the requirements of deep learning. To obtain better results under the condition of few-shot PWC, a small-parameter unit structure and a multi-scale feature-extraction model are proposed. In the small-parameter unit structure, information of adjacent cells is transmitted through state variables. Simultaneously, a forgetting gate is used to update the information and retain long-term dependence of PWC in the form of unit series. The multi-scale feature-extraction model is an integrated model containing three parts. Convolution neural networks are used to extract spatial features of single-period PWC and rhythm features of multi-period PWC. Recursive neural networks are used to retain the long-term dependence features of PWC. Finally, an inference layer is used for classification through extracted features. Classification experiments of cardiovascular diseases are performed on photoplethysmography dataset and continuous non-invasive blood pressure dataset. Results show that the classification accuracy of the multi-scale feature-extraction model on the two datasets respectively can reach 80% and 96%, respectively.