GIS-based landslide susceptibility assessment using random forest and support vector machine models: A case study for Chin State, Myanmar

Comparative study of different machine learning models in landslide susceptibility assessment: A case study of Conghua District, Guangzhou, China

Identification of the geographic origin of peaches by VIS-NIR spectroscopy, fluorescence spectroscopy and image processing technology

Developing machine learning models with multi-source environmental data to predict wheat yield in China

To estimate the compressive strength of cement‐based materials with mining waste, the dataset based on a series of experimental studies was constructed. The support vector machine (SVM), decision tree (DT), and random forest (RF) models were developed and compared. The beetle antennae search (BAS) algorithm was employed to tune the hyperparameters of the developed machine learning models. The predictive performances of the three models were compared by the evaluation of the values of correlation coefficient (R) and root mean square error (RMSE). The results showed that the BAS algorithm can effectively tune these artificial intelligence models. The SVM model can obtain the minimum RMSE, while the BAS algorithm is inefficient in DT and RF models. The SVM, DT, and RF models can be used to predict the compressive strength of cement‐based materials using solid mining waste as aggregate effectively and accurately, with high R values and lower RMSE values. The RF algorithm can obtain the highest value of R and the lowest value of RMSE, demonstrating the highest accuracy. The solid mining waste to cement ratio is the most important variable to affect the compressive strength. Curing time was also an important parameter in the compressive strength of cemented materials, followed by the water‐solid ratio of mining waste and fine sand ratio.

ObjectiveThis study aimed to investigate whether contrast-enhanced computed tomography (CECT) based radiomics analysis could noninvasively predict the perineural invasion (PNI) in esophageal squamous cell carcinoma (ESCC).Methods398 patients with ESCC who underwent resection between February 2016 and March 2020 were retrospectively enrolled in this study. Patients were randomly divided into training and testing cohorts in a 7:3 ratio. Radiomics analysis was performed on the arterial phase images of CECT scans. From these images, 1595 radiomics features were initially extracted. The intraclass correlation coefficient (ICC), wilcoxon rank-sum test, spearman correlation analysis, and boruta algorithm were used for feature selection. Logistic regression (LR), random forest (RF), and support vector machine (SVM) models were established to preidict the PNI status. The performance of these radiomics models was assessed by the area under the receiver operating characteristic curve (AUC). Decision curve analysis (DCA) was conducted to evaluate their clinical utility.ResultsSix radiomics features were retained to build the radiomics models. Among these models, the random forest (RF) model demonstrated superior performance. In the training cohort, the AUC value of the RF model was 0.773, compared to 0.627 for the logistic regression (LR) model and 0.712 for the support vector machine (SVM) model. Similarly, in the testing cohort, the RF model achieved an AUC value of 0.767, outperforming the LR model at 0.638 and the SVM model at 0.683. Decision curve analysis (DCA) suggested that the RF radiomics model exhibited the highest clinical utility.ConclusionsCECT-based radiomics analysis, particularly utilizing the RF, can noninvasively predict the PNI in ESCC preoperatively. This novel approach could enhance patient management by providing personalized information, thereby facilitating the development of individualized treatment strategies for ESCC patients.

Purpose To develop CT-based machine learning radiomics models used for the diagnosis of dysthyroid optic neuropathy (DON). Materials and Methods This is a retrospective study included 57 patients (114 orbits) diagnosed with thyroid-associated ophthalmopathy (TAO) at the Beijing Tongren Hospital between December 2019 and June 2023. CT scans, medical history, examination results, and clinical data of the participants were collected. DON was diagnosed based on clinical manifestations and examinations. The DON orbits and non-DON orbits were then divided into a training set and a test set at a ratio of approximately 7:3. The 3D slicer software was used to identify the volumes of interest (VOI). Radiomics features were extracted using the Pyradiomics and selected by t-test and least absolute shrinkage and selection operator (LASSO) regression algorithm with 10-fold cross-validation. Machine-learning models, including random forest (RF) model, support vector machine (SVM) model, and logistic regression (LR) model were built and validated by receiver operating characteristic (ROC) curves, area under the curves (AUC) and confusion matrix-related data. The net benefit of the models is shown by the decision curve analysis (DCA). Results We extracted 107 features from the imaging data, representing various image information of the optic nerve and surrounding orbital tissues. Using the LASSO method, we identified the five most informative features. The AUC ranged from 0.77 to 0.80 in the training set and the AUC of the RF, SVM and LR models based on the features were 0.86, 0.80 and 0.83 in the test set, respectively. The DeLong test showed there was no significant difference between the three models (RF model vs SVM model: p = .92; RF model vs LR model: p = .94; SVM model vs LR model: p = .98) and the models showed optimal clinical efficacy in DCA. Conclusions The CT-based machine learning radiomics analysis exhibited excellent ability to diagnose DON and may enhance diagnostic convenience.

Prediction of soil salinity parameters using machine learning models in an arid region of northwest China

The traffic safety on expressways is crucial for the efficient operation of the expressway system, and there is a close relationship between traffic states and crashes on expressways, and the occurrence of crashes may be influenced by the interaction of different combinations of traffic states upstream and downstream of the crash location. Based on the crash data and the corresponding traffic flow detector data collected on expressways in Shanghai, this study proposes a hybrid model combining a support vector machine (SVM) model with a k‐means clustering algorithm to predict the likelihood of crashes. The random forest (RF) model is employed to select the important and significant variables for model construction from the data of the traffic flow 5–10 min before the crash occurred. Then, the cross‐validation and transferability of different models (SVM model without variable selection, SVM model with variable selection, and hybrid SVM model with variable selection) are determined using 577 crashes and 5794 matched non‐crash events. The results show that the crash prediction model along with the four most important variables selected using the RF model can obtain a satisfactory prediction performance for crashes. With the combination of the clustering algorithm and SVM model, the accuracy of the crash prediction model can be as high as 78.0%. Moreover, the results of the transferability of the three different models imply that the variable selection and clustering algorithm both have an advantage for crash prediction.

Information fusion and multi-classifier system for miner fatigue recognition in plateau environments based on electrocardiography and electromyography signals

PurposeMachine learning models were developed and validated to identify lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC) using clinical factors, laboratory metrics, and 2-deoxy-2[18F]fluoro-D-glucose ([18F]F-FDG) positron emission tomography (PET)/computed tomography (CT) radiomic features.MethodsOne hundred and twenty non-small cell lung cancer (NSCLC) patients (62 LUAD and 58 LUSC) were analyzed retrospectively and randomized into a training group (n = 85) and validation group (n = 35). A total of 99 feature parameters—four clinical factors, four laboratory indicators, and 91 [18F]F-FDG PET/CT radiomic features—were used for data analysis and model construction. The Boruta algorithm was used to screen the features. The retained minimum optimal feature subset was input into ten machine learning to construct a classifier for distinguishing between LUAD and LUSC. Univariate and multivariate analyses were used to identify the independent risk factors of the NSCLC subtype and constructed the Clinical model. Finally, the area under the receiver operating characteristic curve (AUC) values, sensitivity, specificity, and accuracy (ACC) was used to validate the machine learning model with the best performance effect and Clinical model in the validation group, and the DeLong test was used to compare the model performance.ResultsBoruta algorithm selected the optimal subset consisting of 13 features, including two clinical features, two laboratory indicators, and nine PEF/CT radiomic features. The Random Forest (RF) model and Support Vector Machine (SVM) model in the training group showed the best performance. Gender (P=0.018) and smoking status (P=0.011) construct the Clinical model. In the validation group, the SVM model (AUC: 0.876, ACC: 0.800) and RF model (AUC: 0.863, ACC: 0.800) performed well, while Clinical model (AUC:0.712, ACC: 0.686) performed moderately. There was no significant difference between the RF and Clinical models, but the SVM model was significantly better than the Clinical model. ConclusionsThe proposed SVM and RF models successfully identified LUAD and LUSC. The results indicate that the proposed model is an accurate and noninvasive predictive tool that can assist clinical decision-making, especially for patients who cannot have biopsies or where a biopsy fails.

Airborne geophysical data (AGD) have great potential to represent soil-forming factors. Because of that, the objective of this study was to evaluate the importance of AGD in predicting soil attributes such as aluminum saturation (ASat), base saturation (BS), cation exchange capacity (CEC), clay, and organic carbon (OC). The AGD predictor variables include total count (μR/h), K (potassium), eU (uranium equivalent), and eTh (thorium equivalent), ratios between these elements (eTh/K, eU/K, and eU/eTh), factor F or F-parameter, anomalous potassium (Kd), anomalous uranium (Ud), anomalous magnetic field (AMF), vertical derivative (GZ), horizontal derivatives (GX and GY), and mafic index (MI). The approach was based on applying predictive modeling techniques using (1) digital elevation model (DEM) covariates and Sentinel-2 images with AGD; and (2) DEM covariates and Sentinel-2 images without the AGD. The study was conducted in Bom Jardim, a county in Rio de Janeiro-Brazil with an area of 382,430 km², with a database of 208 soil samples to a predefined depth (0–30 cm). Non-explanatory covariates for the selected soil attributes were excluded. Through the selected covariables, the random forest (RF) and support vector machine (SVM) models were applied with separate samples for training (75%) and validation (25%). The model’s performance was evaluated through the R-squared (R2), root mean square error (RMSE), and mean absolute error (MAE), as well as null model values and coefficient of variation (CV%). The RF algorithm showed better performance with AGD (R2 values ranging from 0.15 to 0.23), as well as the SVM model (R2 values ranging from 0.08 to 0.23) when compared to RF (R2 values ranging from 0.10 to 0.20) and SVM (R2 values ranging from 0.04 to 0.10) models without AGD. Overall, the results suggest that AGD can be helpful for soil mapping. Nevertheless, it is crucial to acknowledge that the accuracy of AGD in predicting soil properties could vary depending on various common factors in DSM, such as the quality and resolution of the covariates and available soil data. Further research is needed to determine the optimal approach for using AGD in soil mapping.

Mangrove ecosystem is providing a substantial amount of ecosystem services (ESs) that has a positive impact on human well-being. Indian Sundarbans is one of the biodiversity hotspots in the world and declared as “World Heritage Site” by UNESCO. The present chapter presents the application of satellite remote sensing data to assess the economic value of the Indian Sundarbans. Ten machine learning (ML) supervised classification models were employed for land use land cover classification and subsequent interpretation. Multiple accuracy assessment tests, including user’s accuracy, producer’s accuracy (PA), kappa statistics, and Jaccard similarity test, were performed for validating the accuracy of the models. Economic valuation of natural capitals was computed using benefits transfer approach. Among the models, maximum likelihood classification (MLC) algorithm has the lowest accuracy observed throughout the study period, except for the year 1973. While the random forest (RF) and support vector machine (SVM) models performed most accurately. Also, among the models, the high similarity is found for SVM, RF, Bayes and artificial neural network (ANN) models. However, a comparably lower similarity estimates had found for MLC model. This suggests the superiority and functional capability of SVM and RF models in capturing land dynamics. For all reference years, the highest ES values (ESVs, in million US$) was found for waste treatment service, followed by erosion control, habitat, food production, disturbance regulation, genetic, soil formation, water supply, recreation, climate regulation, raw material production, water regulation, cultural, nutrient cycling, biological control and pollination services, respectively. The present research has demonstrated that machine models could be a feasible solution for accounting importance of natural capitals across the regions. Secondary sourced freely available remote sensing data are also found highly cost-effective for moderate to large-scale land use decision-making. The valuation approaches and methods adopted in this study could be a reference for future ES studies in other regions and could be replicated easily for similar research interest across the ecosystems.

Geological complexities along mountain highways frequently trigger landslides, posing significant threats to transportation safety and infrastructure. This study evaluates landslide susceptibility along the Lizha-Jiezi section of China’s G345 national highway using Random Forest (RF) and Support Vector Machine (SVM) models. Eleven conditioning factors including altitude, slope, aspect, plan curvature, profile curvature, lithology, distance to fault, rainfall, distance to river, normalized difference vegetation index (NDVI), and distance to road were analyzed using remote sensing and field surveys. A landslide inventory of 67 events was divided into training (70%) and validation (30%) datasets, with non-landslide samples selected at least 100 m away from landslide locations to minimize spatial overlap. Factor contribution analysis identified distance to road as the most significant predictor, highlighting anthropogenic impacts on slope destabilization. Model validation via receiver operating characteristic (ROC) curves demonstrated RF’s superior performance (AUC = 0.887) over SVM (AUC = 0.735). The RF-derived susceptibility map classified five risk levels, revealing high-risk zones concentrated within 200 m of roads, consistent with field observations. Results emphasize the necessity of integrating anthropogenic factors into landslide risk management for mountainous infrastructure. This study provides actionable insights for mitigation strategies and land-use planning, offering a scalable framework adaptable to similar regions.

Snow plays a crucial role in global climate regulation, hydrological processes, and environmental change, making the accurate acquisition of snow depth data highly significant. In this study, we used Sentinel-1 radar data and employed a simulated annealing algorithm to select the optimal influencing factors from radar backscatter characteristics and spatiotemporal geographical parameters within the study area. Snow depth retrieval was subsequently performed using both random forest (RF) and Support Vector Machine (SVM) models. The retrieval results were validated against in situ measurements and compared with the long-term daily snow depth dataset of China for the period 2017–2019. The results indicate that the RF model achieves better agreement with the measured data than existing snow depth products. Specifically, in the Xinjiang region, the RF model demonstrates superior performance, with an R2 of 0.92, a root mean square error (RMSE) of 2.61 cm, and a mean absolute error (MAE) of 1.42 cm. In contrast, the SVM regression model shows weaker agreement with the observations, with an R2 lower than that of the existing snow depth product (0.51) in Xinjiang, and it performs poorly in other regions as well. Overall, the SVM model exhibits deficiencies in both predictive accuracy and spatial stability. This study provides a valuable reference for snow depth retrieval research based on active microwave remote sensing techniques.

Wildfires present a significant threat to ecosystems and human life, requiring effective prevention and response strategies. Equally important is the study of post-fire damages, specifically burnt areas, which can provide valuable insights. This research focuses on the detection and classification of burnt areas and their severity using RGB and multispectral aerial imagery captured by an unmanned aerial vehicle. Datasets containing features computed from multispectral and/or RGB imagery were generated and used to train and optimize support vector machine (SVM) and random forest (RF) models. Hyperparameter tuning was performed to identify the best parameters for a pixel-based classification. The findings demonstrate the superiority of multispectral data for burnt area and burn severity classification with both RF and SVM models. While the RF model achieved a 95.5% overall accuracy for the burnt area classification using RGB data, the RGB models encountered challenges in distinguishing between mildly and severely burnt classes in the burn severity classification. However, the RF model incorporating mixed data (RGB and multispectral) achieved the highest accuracy of 96.59%. The outcomes of this study contribute to the understanding and practical implementation of machine learning techniques for assessing and managing burnt areas.