Comparative assessing the performance of ANN, RF and CNN machine learning methods in identifying landslide prone areas

Landslides are one of the natural hazards in mountainous areas that cause a lot of damage every year, thus, determining the landslide prone area is very important. Integrating deep learning methods can improve satellite image interpretation. This study assessed the performance of artificial neural network (ANN), Random Forest (RF), and Convolutional Neural Network (CNN) methods in identifying landslide prone areas. After pre-processing the satellite images, the educational samples were collected using field visits. Then, the neural network with a modifed structure was used for classification based on the simultaneous integration of the algorithm used. The available data has been divided into 70%, and 30 % for the training and validation stages, respectively. The performance of the generated classification maps of three employed methods were evaluated using the overall accuracy and confusion matrix. The results of evaluating the performance and accuracy of the CNN algorithm for identifying landslide areas show 93% overall accuracy. While the evaluation of the results obtained from ANN and RF methods shows that the overall accuracy of the neural network method is 90% and its overall accuracy is 88% and in the random forest method the overall accuracy is 84% and the overall accuracy is 82%; This study shows that the proposed method has shown the best performance compared to other methods according to evaluation criteria. Compared to the random forest method, the overall accuracy has increased by at least 9% and compared to the artificial neural network by 3%. According to the presented results, the accuracy of the proposed method based on convolution neural network is generally higher than other methods. The most important and main feature of the proposed method is its better and more successful performance in landslide than its other competitors.

Landslides are one of the natural hazards in mountainous areas that cause a lot of damage every year, thus, determining the landslide prone area is very important. Integrating deep learning methods can improve satellite image interpretation. This study assessed the performance of artificial neural network (ANN), Random Forest (RF), and Convolutional Neural Network (CNN) methods in identifying landslide prone areas. After pre-processing the satellite images, the educational samples were collected using field visits. Then, the neural network with a modifed structure was used for classification based on the simultaneous integration of the algorithm used. The available data has been divided into 70%, and 30 % for the training and validation stages, respectively. The performance of the generated classification maps of three employed methods were evaluated using the overall accuracy and confusion matrix. The results of evaluating the performance and accuracy of the CNN algorithm for identifying landslide areas show 93% overall accuracy. While the evaluation of the results obtained from ANN and RF methods shows that the overall accuracy of the neural network method is 90% and its overall accuracy is 88% and in the random forest method the overall accuracy is 84% and the overall accuracy is 82%; This study shows that the proposed method has shown the best performance compared to other methods according to evaluation criteria. Compared to the random forest method, the overall accuracy has increased by at least 9% and compared to the artificial neural network by 3%. According to the presented results, the accuracy of the proposed method based on convolution neural network is generally higher than other methods. The most important and main feature of the proposed method is its better and more successful performance in landslide than its other competitors.

Landslides are one of the natural hazards in mountainous areas that cause a lot of damage every year, thus, determining the landslide prone area is very important. Integrating deep learning methods can improve satellite image interpretation. This study assessed the performance of artificial neural network (ANN), Random Forest (RF), and Convolutional Neural Network (CNN) methods in identifying landslide prone areas. After pre-processing the satellite images, the educational samples were collected using field visits. Then, the neural network with a modifed structure was used for classification based on the simultaneous integration of the algorithm used. The available data has been divided into 70%, and 30 % for the training and validation stages, respectively. The performance of the generated classification maps of three employed methods were evaluated using the overall accuracy and confusion matrix. The results of evaluating the performance and accuracy of the CNN algorithm for identifying landslide areas show 93% overall accuracy. While the evaluation of the results obtained from ANN and RF methods shows that the overall accuracy of the neural network method is 90% and its overall accuracy is 88% and in the random forest method the overall accuracy is 84% and the overall accuracy is 82%; This study shows that the proposed method has shown the best performance compared to other methods according to evaluation criteria. Compared to the random forest method, the overall accuracy has increased by at least 9% and compared to the artificial neural network by 3%. According to the presented results, the accuracy of the proposed method based on convolution neural network is generally higher than other methods. The most important and main feature of the proposed method is its better and more successful performance in landslide than its other competitors.

Landslides are one of the natural hazards in mountainous areas that cause a lot of damage every year, thus, determining the landslide prone area is very important. Integrating deep learning methods can improve satellite image interpretation. This study assessed the performance of artificial neural network (ANN), Random Forest (RF), and Convolutional Neural Network (CNN) methods in identifying landslide prone areas. After pre-processing the satellite images, the educational samples were collected using field visits. Then, the neural network with a modifed structure was used for classification based on the simultaneous integration of the algorithm used. The available data has been divided into 70%, and 30 % for the training and validation stages, respectively. The performance of the generated classification maps of three employed methods were evaluated using the overall accuracy and confusion matrix. The results of evaluating the performance and accuracy of the CNN algorithm for identifying landslide areas show 93% overall accuracy. While the evaluation of the results obtained from ANN and RF methods shows that the overall accuracy of the neural network method is 90% and its overall accuracy is 88% and in the random forest method the overall accuracy is 84% and the overall accuracy is 82%; This study shows that the proposed method has shown the best performance compared to other methods according to evaluation criteria. Compared to the random forest method, the overall accuracy has increased by at least 9% and compared to the artificial neural network by 3%. According to the presented results, the accuracy of the proposed method based on convolution neural network is generally higher than other methods. The most important and main feature of the proposed method is its better and more successful performance in landslide than its other competitors.

Landslides are one of the natural hazards in mountainous areas that cause a lot of damage every year, thus, determining the landslide prone area is very important. Integrating deep learning methods can improve satellite image interpretation. This study assessed the performance of artificial neural network (ANN), Random Forest (RF), and Convolutional Neural Network (CNN) methods in identifying landslide prone areas. After pre-processing the satellite images, the educational samples were collected using field visits. Then, the neural network with a modifed structure was used for classification based on the simultaneous integration of the algorithm used. The available data has been divided into 70%, and 30 % for the training and validation stages, respectively. The performance of the generated classification maps of three employed methods were evaluated using the overall accuracy and confusion matrix. The results of evaluating the performance and accuracy of the CNN algorithm for identifying landslide areas show 93% overall accuracy. While the evaluation of the results obtained from ANN and RF methods shows that the overall accuracy of the neural network method is 90% and its overall accuracy is 88% and in the random forest method the overall accuracy is 84% and the overall accuracy is 82%; This study shows that the proposed method has shown the best performance compared to other methods according to evaluation criteria. Compared to the random forest method, the overall accuracy has increased by at least 9% and compared to the artificial neural network by 3%. According to the presented results, the accuracy of the proposed method based on convolution neural network is generally higher than other methods. The most important and main feature of the proposed method is its better and more successful performance in landslide than its other competitors.

Landslides are one of the natural hazards in mountainous areas that cause a lot of damage every year, thus, determining the landslide prone area is very important. Integrating deep learning methods can improve satellite image interpretation. This study assessed the performance of artificial neural network (ANN), Random Forest (RF), and Convolutional Neural Network (CNN) methods in identifying landslide prone areas. After pre-processing the satellite images, the educational samples were collected using field visits. Then, the neural network with a modifed structure was used for classification based on the simultaneous integration of the algorithm used. The available data has been divided into 70%, and 30 % for the training and validation stages, respectively. The performance of the generated classification maps of three employed methods were evaluated using the overall accuracy and confusion matrix. The results of evaluating the performance and accuracy of the CNN algorithm for identifying landslide areas show 93% overall accuracy. While the evaluation of the results obtained from ANN and RF methods shows that the overall accuracy of the neural network method is 90% and its overall accuracy is 88% and in the random forest method the overall accuracy is 84% and the overall accuracy is 82%; This study shows that the proposed method has shown the best performance compared to other methods according to evaluation criteria. Compared to the random forest method, the overall accuracy has increased by at least 9% and compared to the artificial neural network by 3%. According to the presented results, the accuracy of the proposed method based on convolution neural network is generally higher than other methods. The most important and main feature of the proposed method is its better and more successful performance in landslide than its other competitors.