Effects of non-landslide sampling strategies on machine learning models in landslide susceptibility mapping

Landslide susceptibility and building exposure assessment using machine learning models and geospatial analysis techniques

The research location is in the Purwanegara Subdistrict, Banjarnegara Regency, Province of Central Java. According to the Geological Agency of Indonesia, this location is a landslide-prone area, and many landslides occur yearly. Therefore, it needs a landslide susceptibility map is basic information for landslide mitigation in this area. The parameters used in this research are slope, lithology, distance from structural geology, distance from the river, land use, and rainfall. Using six parameters, the weight of evidence (WoE) method was used to develop a landslide susceptibility map. This research aims to make a zonation of landslide susceptibility in this area. The data were collected by field survey and visiting some related institutions. The landslide data used are 85 landslide events in the last three years. All data was then randomly divided into two groups: 70% as model data sets and 30% as validation data sets. The map of every parameter will be overlaid to create a landslide susceptibility zone. The Area Under Curve (AUC) method validated the final map. The result shows that landslide susceptibility zonation can be divided into four zones: very low susceptibility zone, low susceptibility zone, medium susceptibility zone, and high susceptibility zone. The very low susceptibility zone is mostly located in the north, the low susceptibility zone is mostly in the north and south, the moderate susceptibility zone is in the middle, and the high susceptibility zone is in the middle of the research’s location. The validation results of the success and prediction rates using the AUC method show an accuracy value of 0.86 and 0.82, respectively. According to the validation result, both can be classified as very good.

Machine learning-based landslide susceptibility assessment with optimized ratio of landslide to non-landslide samples

The accuracy of data-driven landslide susceptibility mapping (LSM) is closely affected by the quality of non-landslide samples. This research proposes a method combining a self-organizing-map (SOM) and a one-class SVM (SOM-OCSVM) to generate more reasonable non-landslide samples. We designed two steps: first, a random selection, a SOM network, a one class SVM model, and a SOM-OCSVM model were used to generate non-landslide sample datasets. Second, four machine learning models (MLs)—namely logistic regression (LRG), multilayer perceptron (MLP), support vector machine (SVM), and random forest (RF)—were used to verify the effects of four non-landslide sample datasets on LSM. From the region along the Sichuan-Tibet Highway, we selected 11 conditioning factors and 1186 investigated landslides to perform the aforementioned experiments. The results show that the SOM-OCSVM method achieves the highest AUC (>0.94) and minimum standard deviation (<0.081) compared with other methods. Moreover, RF achieves the best performance in different datasets compared with other ML models. The aforementioned results prove that the proposed method can enhance the performance of ML models to produce more reliable LSM.

Developing effective strategies to predict areas susceptible to landslides and reducing risk is vital. This involves using ensemble methods to meet the precise prediction and addressing challenges like data limitation. Recent studies have highlighted the potential of using ensemble methods to enhance the prediction of landslide susceptibility maps (LSM). Ensemble methods present a sampling of landslides and non-landslide points from high and low susceptible areas, respectively. Extensive research has explored their application in machine learning processes, particularly in classification-related problems. This study delves into strategies of ensemble as a promising method in future landslide applications. The proposed method was tested considering Kangra district of Himachal Pradesh as study area where three datasets were prepared consisting of presence and absence points. Dataset 1 consisted of initial landslide and randomly generated non-landslide points. In dataset 2, additional landslide points obtained from the very high susceptibility of initial LSM were supplemented with initial landslide data, while the non-landslide points were generated randomly from the study area. Finally, dataset 3 was composed of the landslide points as in dataset 2, and the non-landslide points were obtained from the very low susceptible areas of initial LSM. These datasets are used with random forest (RF) and support vector machine (SVM), thereby preparing six landslide susceptibility maps. To analyze the applicability of the proposed method, we have used metrics such as AUC-ROC, precision, recall, F-score, accuracy and Mathew's correlation coefficient (MCC). The AUC for dataset 1 with SVM and RF is 0.89, which increased to 0.898 and 0.952 for datasets 2 and 3 with SVM and 0.937 and 0.954 with RF. Among all the methods, the precision and recall values were highest for dataset 3 with SVM as well as RF. Hence, based on several accuracy metrics, we conclude that when the landslides and non-landslides samples were sampled from very high and very low susceptible areas respectively, the LSM performed better than all the other methods. Sampling landslides from very high susceptible areas only (dataset 2) does not perform well thereby committing misclassification error. The study demonstrated that the landslide and non-landslide data were obtained from very high and very low susceptibility; the predictive capability of the LSM increased significantly. Thus, the results demonstrate the effectiveness of the proposed ensemble approach in providing precise delineation of landslide zones, facilitating informed decision-making for land and hazard management.

Landslide is a devastating natural disaster, causing loss of life and property. It is likely to occur more frequently due to increasing urbanization, deforestation, and climate change. Landslide susceptibility mapping is vital to safeguard life and property. This article surveys machine learning (ML) models used for landslide susceptibility mapping to understand the current trend by analyzing published articles based on the ML models, landslide causative factors (LCFs), study location, datasets, evaluation methods, and model performance. Existing literature considered in this comprehensive survey is systematically selected using the ROSES protocol. The trend indicates a growing interest in the field. The choice of LCFs depends on data availability and case study location; China is the most studied location, and area under the receiver operating characteristic curve (AUC) is considered the best evaluation metric. Many ML models have achieved an AUC value > 0.90, indicating high reliability of the susceptibility map generated. This paper also discusses the recently developed hybrid, ensemble, and deep learning (DL) models in landslide susceptibility mapping. Generally, hybrid, ensemble, and DL models outperform conventional ML models. Based on the survey, a few recommendations and future works which may help the new researchers in the field are also presented.

Landslide is a part of natural natural disasters that causes fatalities to humans, destroys property and overwhelms the regional economy. Various landslide evaluation attempts have been utilized to determine the landslide susceptibility values. Machine learning (ML) has been used in numerous research areas including geotechnical disciplines to produce an effective model to resolve the geotechnical challenge. The ML model has been adopted to produce a landslide susceptibility map (LSM) in many studies with various types and algorithms. This review paper discusses the ML approach used to develop LSM with specific approaches: Support Vector Machine (SVM). The basic principle of ML in producing the LSM is determined and discussed. The study also provides information on the types of validation and performance of the model in developing LSM. SVM and its hybrid model were found to yield good performance in producing LSM in most of the studies with SVM outperforming most of the other ML approaches. This research contributes to the landslide mapping field by providing a readily available, State-of-the-Art reference for researchers, practitioners and local authorities in producing efficient and reliable LSM based on the SVM principle.

Landslides cause significant damage to infrastructure and loss of life. Landslide susceptibility map (LSM), as an important reference for landslide hazard assessment, indicates prone areas of landslides. However, conventional LSM only predicts the spatial distribution of potential landslides, which cannot fully explain the occurrence of landslides at different times. In the present study, a spatiotemporal LSM is conducted to predict landslides both in space and time. A landslide database containing 223 recorded landslide events in southwestern Pennsylvania is used. Fourteen topographic spatial factors and eight rainfall temporal factors are used for machine learning (ML). Four ML models are applied in the study, including Logistic regression (LR), Support vector machine (SVM), Random forest (RF), and Gradient boosting machine (GBM). The results show that through cross-validation, RF outperforms the other algorithms with a value 0.86 of the area under the receiver operating characteristic curve (AUC score). The optimal model is used to generate spatiotemporal LSMs. It is concluded that by introducing spatial and temporal information simultaneously, ML models have the capability of learning the pattern of landslide occurrence both in space and time, providing an effective assessment tool to reduce catastrophic loss of landslide hazards.

This study focuses on using various machine learning (ML) models to evaluate the shear behaviors of ultra-high-performance concrete (UHPC) beams reinforced with glass fiber-reinforced polymer (GFRP) bars. The main objective of the study is to predict the shear strength of UHPC beams reinforced with GFRP bars using ML models. We use four different ML models: support vector machine (SVM), artificial neural network (ANN), random forest (R.F.), and extreme gradient boosting (XGBoost). The experimental database used in the study is acquired from various literature sources and comprises 54 test observations with 11 input features. These input features are likely parameters related to the composition, geometry, and properties of the UHPC beams and GFRP bars. To ensure the ML models' generalizability and scalability, random search methods are utilized to tune the hyperparameters of the algorithms. This tuning process helps improve the performance of the models when predicting the shear strength. The study uses the ACI318M-14 and Eurocode 2 standard building codes to predict the shear capacity behavior of GFRP bars-reinforced UHPC I-shaped beams. The ML models' predictions are compared to the results obtained from these building code standards. According to the findings, the XGBoost model demonstrates the highest predictive test performance among the investigated ML models. The study employs the SHAP (SHapley Additive exPlanations) analysis to assess the significance of each input parameter in the ML models' predictive capabilities. A Taylor diagram is used to statistically compare the accuracy of the ML models. This study concludes that ML models, particularly XGBoost, can effectively predict the shear capacity behavior of GFRP bars-reinforced UHPC I-shaped beams.

The purpose of this paper is to map the landslide susceptibility using the fuzzy gamma operator and GIS for the section of the national road n°11 linking Mateur to Beja. To minimize the subjectivity of the fuzzy logic approach, the frequency ratio was used to calculate the fuzzy membership. To locate the 147 landslides, Google Earth extracts analysis, and field survey has been done. In this cartography, nine factors controlling landslides were used: slope, aspect, curvature plane, curvature profile, distance to faults, distance to rivers, land use, rainfall, and lithology. Once the fuzziness is calculated in each factor using the frequency ratio (FR), the fuzzy gamma operator can be applied to these nine factors to produce the landslide susceptibility map. Finally, the choice of the nearest susceptibility map of reality is made by applying the ROC curve. By the analysis of the area under curve (AUC), it is seen that the prediction accuracy of model proves that the gamma value of 0.90 yielded the better prediction of landslide susceptibility map (0.89). Finally, our area of interest was classified based on the Jenks natural breaks classification method into five classes, such as non-susceptible zone, low susceptible zone, moderate susceptible zone, high susceptible zone, and very high susceptible zone. Landslide susceptibility mapping based on the fuzzy gamma operator presents a very acceptable result with a reliability of 89%.

The prediction of wind energy generation is important to enhance the performance and dependability of renewable energy systems due to the rising demand for wind-generated electricity and advancements in wind energy technology competitiveness. This study leverages advanced machine learning (ML) and some other statistical and deep learning based time series forecasting models to enhance the accuracy of wind energy predictions. This comprehensive analysis includes nine ML models—Linear Regression, Random Forests (RF), Gradient Boosting Machines (GBM), Support Vector Machines (SVM), K-Nearest Neighbors (KNN), AdaBoost, XGBoost, Support Vector Regression (SVR), and Neural Networks—as well as Four time-series forecasting models—ARIMA, Temporal Convolutional Networks (TCNs), Long Short-Term Memory (LSTM) networks and GRU. Each ML model underwent rigorous cross-validation to ensure optimal performance. The assessment criteria utilized here comprised the Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and the R² Score. It was found that among the nine ML models, Random Forests, GBM and KNN consistently provided superior accuracy and robustness, making them the top choices for wind energy prediction whereas the performance of linear regression, SVM and SVR were very poor for the considered dataset. From the experiment, Random Forest, GBM, and KNN showed the best performance with low MSE values of 0.77, 1.95, and 1.51 respectively, while other models had MSEs above 7.5, with AdaBoost reaching 30. Their RMSEs (0.88, 1.40, 1.23) and MAEs (0.093, 0.73, 0.10) also indicate strong predictive accuracy compared to the rest.In this paper, time series forecasting, TCNs, LSTM and GRU networks showed strong capabilities in capturing temporal dependencies and trends within the wind energy data. Visualization techniques were employed to compare model performances comprehensively, providing clear insights into their predictive power. Therefore, this present study offers a robust framework for researchers and practitioners aiming to leverage machine learning and time series forecasting in the realm of renewable energy prediction.

647 Background: The primary treatment of most mNSTC is chemotherapy followed by surgery if the residual disease (RD) is >1 cm. However, conventional imaging lacks the specificity to characterize the tissue, often leading to overtreatment. This study hypothesizes that integrating CT-driven radiomics features with plasma miR371 and miR375 will enhance the predictive accuracy of Machine Learning (ML) models to predict teratoma, viable germ cell (vGCT) and fibrosis/necrosis (F/N) in mNSTC patients with RD. Methods: 111 lesions from52 patients, including residual teratoma (n=57), F/N (n=33), vGCT (n=10), and additional seminoma (n=11) for training purposes were included, split into training (N=78) and test cohorts (N=33). Lesions were lymph nodes (n=87), lung (n=21), and brain (n=3) with a median size of 1.6 cm (Q1-Q3 interval=1.2-2.73 cm). 3D Slicer version 5.6.1 was used to segment the RD > 1 cm (short axis) and extract radiomics features. Plasma miRNA levels before resection were measured by RT-PCR. Random Forest (RF), Support Vector Machine (SVM), Gradient Boosting (GB), and CatBoost (CB) ML models were evaluated to define the operating characteristics of radiomics alone (R-only) and in combination with miR371 (371) and/or miR375 (375) levels in predicting teratoma, vGCT and F/N. Results: For predicting teratoma, the best models were RF (R+375 and R+371+375), CB (R+371+375), and GB (R+371 and R+371+375). While adding miR371 or miR375 to R-only slightly improved AUC across models, the best results were achieved with the R+375+371 dataset. CB achieved AUCs ranging from 0.94 to 0.97 in training and 0.81 to 0.93 in test sets, with its highest AUC of 0.93 (95% CI: 0.78-0.97) on the R+375+371 dataset to differentiate all three classes. Similarly, GB demonstrated strong performance, achieving its highest AUC of 0.93 (95% CI: 0.79-0.96) on the R+375+371 dataset (Table). Conclusions: Integration of plasma miR371, miR375 and radiomics improved accuracy of predicting histologies across all ML models. These methods could be used to characterize the histology of RD in mNSTC patients to better inform treatment decisions. Further refinement, including incorporation of histological findings of the primary tumor, will be reported. AUC values of different ML algorithms on training and test sets. TRAINING SET TEST SET Model ±SD R R+375 R+371 R+375+371 Model (95% CI) R R+375 R+371 R+375+371 RF 0.93±0.05 0.95±0.04 0.95±0.03 0.96±0.04 RF 0.8(0.59-0.89) 0.85(0.72-0.93) 0.87(0.76-0.95) 0.91(0.78-0.95) SVM 0.84±0.06 0.84±0.09 0.89±0.11 0.89±0.09 SVM 0.72(0.54-0.80) 0.74(0.56-0.82) 0.83(0.69-0.92) 0.84(0.76-0.94) GB 0.94±0.04 0.91±0.08 0.95±0.05 0.97±0.03 GB 0.84(0.61-0.96) 0.89(0.77-0.97) 0.89(0.79-0.96) 0.93(0.79-0.96) CB 0.95±0.03 0.94±0.03 0.94±0.04 0.97±0.03 CB 0.81(0.6-0.93) 0.86(0.73-0.94) 0.89(0.78-0.97) 0.93(0.78-0.97)

This study proposes a novel predictive approach for constructing landslide susceptibility maps by combining boosting models with hyperparameters optimized using Optuna. We used a well-defined spatial database comprising 128 landslides and 22 factors affecting landslides in the Eunsan village, Buyeo City, Chungcheong Province, Korea. Optuna is an open-source hyperparameter optimization framework for automating the determination of the best hyperparameters for machine learning (ML) models. The results demonstrate the excellent performance of three ML models optimized using Optuna. The LightGBM model exhibited the highest accuracy (a receiver operating characteristic value of 0.932) among the three models, followed by the XGBoost model (0.926) and the random forest model (0.917). These ML models highlight the significance of hyperparameter tuning and selection using Optuna. The efficiency, ease of use, and flexibility of Optuna make it a powerful tool for optimizing ML models and accelerating the research and development process in the field of ML and artificial intelligence. This study emphasizes the potential of these approaches as optimized tools for landslide susceptibility mapping.

In recent years, a significant amount of research has focused on analyzing the effectiveness of machine learning (ML) models for malware detection. These approaches have ranged from methods such as decision trees and clustering to more complex approaches like support vector machine (SVM) and deep neural networks. In particular, neural networks have proven to be very effective in detecting complex and advanced malware. This, however, comes with a caveat. Neural networks are notoriously complex. Therefore, the decisions that they make are often just accepted without questioning why the model made that specific decision. The black box characteristic of neural networks has challenged researchers to explore methods to explain black-box models such as SVM and neural networks and their decision-making process. Transparency and explainability give the experts and malware analysts assurance and trustworthiness about the ML models’ decisions. In addition, it helps in generating comprehensive reports that can be used to enhance cyber threat intelligence sharing. As such, this much needed analysis drives our work in this paper to explore the explainability and interpretability of ML models in the field of online malware detection. In this paper, we used the Shapley Additive exPlanations (SHAP) explainability technique to achieve efficient performance in interpreting the outcome of different ML models such as SVM Linear, SVM-RBF (Radial Basis Function), Random Forest (RF), Feed-Forward Neural Net (FFNN), and Convolutional Neural Network (CNN) models trained on an online malware dataset. To explain the output of these models, explainability techniques such as KernalSHAP, TreeSHAP, and DeepSHAP are applied to the obtained results.

Integrated STEM projects and experiments promote interdisciplinary learning, enhance critical thinking, and prepare students for real-world problem-solving by bridging science, technology, engineering, and mathematics. While numerous research studies have explored the STEM education domain, few have focused on supporting educators in identifying and designing effective integrated STEM projects and experiments. This research addresses this gap by introducing a novel system that leverages machine learning (ML) and large language models (LLMs) to assist educators in classifying and creating integrated STEM projects.We created and labeled a dataset of 1,071 project descriptions in this research work, mapped to one or more STEM areas (Science, Technology, Engineering, Mathematics). The dataset was developed using manually curated records, harvesting online sources, and synthetic data generation. Natural Language Processing (NLP) techniques were applied to prepare project descriptions for analysis. Various ML models, including Random Forest, Support Vector Machines (SVM), Logistic Regression, and Naive Bayes, were used for multi-label classification. The Random Forest model achieved the best performance, with a Precision of 91.99%, Recall of 94.59%, F1 Score of 93.27%, and Hamming Loss of 6.74%.The system operates in two phases: In Phase 1, the instructor proposes a project title with a description, and in response, the ML model identifies one or more STEM areas as the most relevant. In Phase 2, ChatGPT, specifically GPT-4o, assists educators by defining experiment objectives, generating ideas, designing procedures, and suggesting tools and resources. This human-in-the-loop system enhances collaboration between educators, ML models, and LLMs, streamlining the design of effective integrated STEM projects.This work's implications extend to improving the accessibility and effectiveness of integrated STEM education by reducing the barriers educators face in designing interdisciplinary projects. It provides a scalable framework for integrating advanced AI techniques into educational practices and fostering classroom innovation.