Convolutional neural network based hurricane damage detection using satellite images

Building loss assessment using deep learning algorithm from typhoon Rusa

Climate crises such as extreme weather events, natural disasters and climate change caused by climate transformations are causing much damage worldwide enough to be called a climate catastrophe. The private sector and the government across industries are making every effort to prevent and limit the increasing damage, but the results have yet to meet market demand. Therefore, this study proposes a method that uses a deep learning algorithm to predict the damage caused by typhoons. Model development is based on a Deep Neural Network (DNN) algorithm, and learning data is obtained by fine-tuning the network structure and hyperparameters; the amount of damage caused by Typhoon Rusa was known as training data. The constructed DNN model underwent evaluation and validation by computation of mean absolute error (MAE) and root mean square error (RMSE). Furthermore, a comparative analysis was conducted to confirm the applicability of the proposed framework against a traditional multi-regression model to ensure the model's accuracy and resilience. Finally, this study offers a novel approach to predicting typhoon damage using advanced deep-learning techniques. Subsequently, government disaster management officials, facility managers, and insurance companies can utilize this method to accurately predict the extent of damage caused by typhoons. Preventive actions such as improved risk assessment, expanded insurance companies, and enhanced disaster responses plans can be implemented using these outcomes. Ultimately, the proposed model will help to reduce typhoon damage and strengthen general resilience to climate crises.

ResRandSVM: Hybrid Approach for Acute Lymphocytic Leukemia Classification in Blood Smear Images

Acute Lymphocytic Leukemia is a type of cancer that occurs when abnormal white blood cells are produced in the bone marrow which do not function properly, crowding out healthy cells and weakening the immunity of the body and thus its ability to resist infections. It spreads quickly in children's bodies, and if not treated promptly it may lead to death. The manual detection of this disease is a tedious and slow task. Machine learning and deep learning techniques are faster than manual detection and more accurate. In this paper, a deep feature selection-based approach ResRandSVM is proposed for the detection of Acute Lymphocytic Leukemia in blood smear images. The proposed approach uses seven deep-learning models: ResNet152, VGG16, DenseNet121, MobileNetV2, InceptionV3, EfficientNetB0 and ResNet50 for deep feature extraction from blood smear images. After that, three feature selection methods are used to extract valuable and important features: analysis of variance (ANOVA), principal component analysis (PCA), and Random Forest. Then the selected feature map is fed to four different classifiers, Adaboost, Support Vector Machine, Artificial Neural Network and Naïve Bayes models, to classify the images into leukemia and normal images. The model performs best with a combination of ResNet50 as a feature extractor, Random Forest as feature selection and Support Vector Machine as a classifier with an accuracy of 0.900, precision of 0.902, recall of 0.957 and F1-score of 0.929.

Transfer Learning-Based Automatic Hurricane Damage Detection Using Satellite Images

After the occurrence of a hurricane, assessing damage is extremely important for the emergency managers so that relief aid could be provided to afflicted people. One method of assessing the damage is to determine the damaged and the undamaged buildings post-hurricane. Normally, damage assessment is performed by conducting ground surveys, which are time-consuming and involve immense effort. In this paper, transfer learning techniques have been used for determining damaged and undamaged buildings in post-hurricane satellite images. Four different transfer learning techniques, which include VGG16, MobileNetV2, InceptionV3 and DenseNet121, have been applied to 23,000 Hurricane Harvey satellite images, which occurred in the Texas region. A comparative analysis of these models has been performed on the basis of the number of epochs and the optimizers used. The performance of the VGG16 pre-trained model was better than the other models and achieved an accuracy of 0.75, precision of 0.74, recall of 0.95 and F1-score of 0.83 when the Adam optimizer was used. When the comparison of the best performing models was performed in terms of various optimizers, VGG16 produced the best accuracy of 0.78 for the RMSprop optimizer.