Landslides are a major natural hazard that is difficult to predict due to the complex and varying factors that contribute to slope stability. However, artificial neural networks (ANN) have shown promise in improving prediction accuracy. In this study, researchers introduce a new approach called superposable neural network (SNN) optimization, which combines interpretability, high accuracy, high generalizability, and low model complexity. To validate their approach, the researchers trained SNN models on landslide inventory data from three different regions in the easternmost Himalaya. The SNN models outperformed physically-based and statistical models and achieved similar performance to state-of-the-art deep neural networks. The analysis revealed that the product of slope and precipitation as well as hillslope aspect were important contributors to high landslide susceptibility. This highlights the significance of strong slope-climate couplings and microclimates in landslide occurrences. The researchers also conducted validation tests using synthetic datasets which demonstrated the ability of the SNN models to identify contributing features and extract their functions from the data. The SNN optimization algorithm used in this study is described in detail. The easternmost Himalaya region is particularly susceptible to landslides due to steep slopes, extreme precipitation events, flooding, and frequent earthquakes. The researchers generated a landslide inventory for this region by combining manual delineation with a semi-automatic detection algorithm which included 2289 mapped landslides with varying sizes across three specific regions within: N-S region (Dibang), E-W region (Lohit), and NW-SE region (range front). By testing the SNN model on these regions with different environmental conditions they aimed to identify universal or distinct controls of landslides as well as similarities or differences in feature contributions across these regions. The SNN model utilized 15 single features including aspects such as elevation, slope mean annual precipitation and distance to channels and faults which were selected based on previous studies that examined landslide susceptibility. They also compared its performance against individual classifiers for each feature as well as a physically based slope stability model (SHALSTAB). In conclusion this study provides valuable insights into the contributing factors of landslides by demonstrating the effectiveness of SNN models in predicting landslide occurrences with high accuracy and interpretability while highlighting the innovative approach of using superposable neural network optimization for assessing landslide susceptibility in the easternmost Himalaya region.
- Landslides are a major natural hazard that is difficult to predict
- Artificial neural networks (ANN) have shown promise in improving prediction accuracy
- Researchers introduce a new approach called superposable neural network (SNN) optimization
- SNN models outperformed physically-based and statistical models
- SNN models achieved similar performance to state-of-the-art deep neural networks
- Slope and precipitation, as well as hillslope aspect, were important contributors to high landslide susceptibility
- Strong slope-climate couplings and microclimates play a significant role in landslide occurrences
- SNN models can identify contributing features and extract their functions from the data
- The easternmost Himalaya region is particularly susceptible to landslides due to various factors such as steep slopes, extreme precipitation events, flooding, and earthquakes
- The researchers generated a landslide inventory for this region using manual delineation and a semi-automatic detection algorithm
- The SNN model utilized 15 single features including elevation, slope mean annual precipitation, distance to channels and faults
- The study provides valuable insights into the contributing factors of landslides in the easternmost Himalaya region.
Landslides are when the ground moves suddenly and can be dangerous. Artificial neural networks (ANN) are computer programs that help predict landslides better. Researchers made a new way called superposable neural network (SNN) to improve predictions even more. SNN models were better than other models at predicting landslides. SNN models did just as well as deep neural networks, which are also good at predicting things. The shape of the land and how much rain it gets are important for landslides. The easternmost Himalaya region is very likely to have landslides because of steep slopes, lots of rain, floods, and earthquakes. The researchers looked at many different things like elevation and rainfall to understand why landslides happen there."
Definitions
- Landslide: When the ground suddenly moves.
- Artificial neural networks (ANN): Computer programs that help predict things.
- Superposable neural network (SNN): A new way to make predictions better.
- Prediction: Guessing what will happen in the future.
- Deep neural networks: Another type of computer program that is good at predicting things.
- Slope: How steep or flat the land is.
- Precipitation: Rainfall or snowfall.
- Susceptibility: How likely something is to happen.
- Contributing factors: Things that make something more likely to happen.
- Elevation: How high or low the land is compared to sea level.
- Semi-automatic detection algorithm: A computer program that
Landslide Susceptibility in the Easternmost Himalaya Region: A Superposable Neural Network Optimization Approach
Landslides are a major natural hazard that is difficult to predict due to the complex and varying factors that contribute to slope stability. Artificial neural networks (ANN) have shown promise in improving prediction accuracy, but there is still room for improvement. In this study, researchers introduce a new approach called superposable neural network (SNN) optimization which combines interpretability, high accuracy, high generalizability, and low model complexity. The SNN models were tested on landslide inventory data from three different regions in the easternmost Himalaya region with varied environmental conditions to identify universal or distinct controls of landslides as well as similarities or differences in feature contributions across these regions.
Background
The easternmost Himalaya region is particularly susceptible to landslides due to steep slopes, extreme precipitation events, flooding, and frequent earthquakes. To better understand the contributing factors of landslides in this region and improve prediction accuracy of landslide occurrences researchers developed a SNN model using 15 single features including elevation, slope mean annual precipitation and distance to channels and faults which were selected based on previous studies that examined landslide susceptibility. They also compared its performance against individual classifiers for each feature as well as a physically based slope stability model (SHALSTAB).
Methodology
The researchers generated a landslide inventory for this region by combining manual delineation with a semi-automatic detection algorithm which included 2289 mapped landslides with varying sizes across three specific regions within: N-S region (Dibang), E-W region (Lohit), and NW-SE region (range front). The SNN model was then trained on these datasets using an optimization algorithm described in detail below:
• The input layer consists of 15 nodes representing each single feature used for training
• A hidden layer consisting of 10 neurons was added between the input layer and output layer
• An activation function such as sigmoid or ReLU was applied after every neuron
• A softmax activation function was applied at the output layer
• Backpropagation algorithms such as Adam optimizer or RMSprop were used during training
• Finally regularization techniques such as dropout were employed during training process
Results & Discussion
The results showed that the SNN models outperformed physically-based and statistical models achieving similar performance to state-of-the-art deep neural networks while providing greater interpretability than other methods. The analysis revealed that the product of slope and precipitation as well as hillslope aspect were important contributors to high landslide susceptibility highlighting their significance when it comes to strong slope climate couplings and microclimates in landslide occurrences. Furthermore validation tests conducted using synthetic datasets demonstrated the ability of SNN models to identify contributing features accurately extract their functions from data thus confirming its effectiveness at predicting landslide occurrences with high accuracy while providing insights into contributing factors behind them.
Conclusion
This study provides valuable insights into understanding contributing factors behind landslides by demonstrating how effective SNN models can be at predicting them with high accuracy while providing greater interpretability than other methods available today through its innovative approach utilizing superposable neural network optimization specifically tailored towards assessing landslide susceptibility in easternmost Himalayan regions where they are most prone occurances due its unique topography combined with extreme weather conditions making it particularly vulnerable area when it comes natural disasters like these .
