Knowledge-infused Deep Learning Enables Interpretable Landslide Forecasting

• URL: http://arxiv.org/abs/2307.08951v1
• Date: Tue, 18 Jul 2023 03:39:03 GMT
• Title: Knowledge-infused Deep Learning Enables Interpretable Landslide Forecasting
• Authors: Zhengjing Ma, Gang Mei
• Abstract summary: Recent development of transformer-based deep learning offers untapped possibilities for forecasting landslides. We present a deep learning pipeline that is capable of predicting landslide behavior holistically. We validate our approach by training models to forecast reservoir landslides in the Three Gorges Reservoir and creeping landslides on the Tibetan Plateau.
• Score: 0.019036571490366496
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Forecasting how landslides will evolve over time or whether they will fail is a challenging task due to a variety of factors, both internal and external. Despite their considerable potential to address these challenges, deep learning techniques lack interpretability, undermining the credibility of the forecasts they produce. The recent development of transformer-based deep learning offers untapped possibilities for forecasting landslides with unprecedented interpretability and nonlinear feature learning capabilities. Here, we present a deep learning pipeline that is capable of predicting landslide behavior holistically, which employs a transformer-based network called LFIT to learn complex nonlinear relationships from prior knowledge and multiple source data, identifying the most relevant variables, and demonstrating a comprehensive understanding of landslide evolution and temporal patterns. By integrating prior knowledge, we provide improvement in holistic landslide forecasting, enabling us to capture diverse responses to various influencing factors in different local landslide areas. Using deformation observations as proxies for measuring the kinetics of landslides, we validate our approach by training models to forecast reservoir landslides in the Three Gorges Reservoir and creeping landslides on the Tibetan Plateau. When prior knowledge is incorporated, we show that interpretable landslide forecasting effectively identifies influential factors across various landslides. It further elucidates how local areas respond to these factors, making landslide behavior and trends more interpretable and predictable. The findings from this study will contribute to understanding landslide behavior in a new way and make the proposed approach applicable to other complex disasters influenced by internal and external factors in the future.

Related papers

• Landslide vulnerability analysis using frequency ratio (FR) model: a study on Bandarban district, Bangladesh [0.0]
  This study assesses landslide vulnerability in the Chittagong Hill Tracts (CHT), specifically focusing on Bandarban district in Southeast Bangladesh. The analysis revealed that steep slopes, high elevations, specific aspects, and curvature contribute significantly to landslide susceptibility. The resulting Landslide Susceptibility Map (LSM) categorized the area into five susceptibility zones.
  arXiv  Detail & Related papers  (2024-07-15T16:28:10Z)
• Interpretability of Statistical, Machine Learning, and Deep Learning Models for Landslide Susceptibility Mapping in Three Gorges Reservoir Area [4.314875317825748]
  Landslide susceptibility mapping (LSM) is crucial for identifying high-risk areas and informing prevention strategies. This study investigates the interpretability of statistical, machine learning (ML), and deep learning (DL) models in predicting landslide susceptibility.
  arXiv  Detail & Related papers  (2024-05-20T03:46:42Z)
• Interpretable Knowledge Tracing via Response Influence-based Counterfactual Reasoning [10.80973695116047]
  Knowledge tracing plays a crucial role in computer-aided education and intelligent tutoring systems. Current approaches have explored psychological influences to achieve more explainable predictions. We propose RCKT, a novel response influence-based counterfactual knowledge tracing framework.
  arXiv  Detail & Related papers  (2023-12-01T11:27:08Z)
• Landslide Topology Uncovers Failure Movements [1.08890978642722]
  We present an approach for identifying failure types based on their movements, e.g., slides and flows. We observe topological proxies reveal prevalent signatures of mass movement mechanics embedded in the landslide's morphology or shape. We can identify failure types in historic and event-specific landslide databases with 80 to 94 % accuracy.
  arXiv  Detail & Related papers  (2023-10-14T17:53:55Z)
• Performative Time-Series Forecasting [71.18553214204978]
  We formalize performative time-series forecasting (PeTS) from a machine-learning perspective. We propose a novel approach, Feature Performative-Shifting (FPS), which leverages the concept of delayed response to anticipate distribution shifts. We conduct comprehensive experiments using multiple time-series models on COVID-19 and traffic forecasting tasks.
  arXiv  Detail & Related papers  (2023-10-09T18:34:29Z)
• Interpretable Imitation Learning with Dynamic Causal Relations [65.18456572421702]
  We propose to expose captured knowledge in the form of a directed acyclic causal graph. We also design this causal discovery process to be state-dependent, enabling it to model the dynamics in latent causal graphs. The proposed framework is composed of three parts: a dynamic causal discovery module, a causality encoding module, and a prediction module, and is trained in an end-to-end manner.
  arXiv  Detail & Related papers  (2023-09-30T20:59:42Z)
• Dynamic landslide susceptibility mapping over recent three decades to uncover variations in landslide causes in subtropical urban mountainous areas [17.570791791237387]
  This study presents dynamic landslide susceptibility mapping that simply employs multiple predictive models for annual LSA. The chosen study area is Lantau Island, Hong Kong, where we conducted a comprehensive dynamic LSA spanning from 1992 to 2019.
  arXiv  Detail & Related papers  (2023-08-23T05:33:03Z)
• A Comprehensive Survey of Forgetting in Deep Learning Beyond Continual Learning [76.47138162283714]
  Forgetting refers to the loss or deterioration of previously acquired information or knowledge. Forgetting is a prevalent phenomenon observed in various other research domains within deep learning. Survey argues that forgetting is a double-edged sword and can be beneficial and desirable in certain cases.
  arXiv  Detail & Related papers  (2023-07-16T16:27:58Z)
• Latent Traversals in Generative Models as Potential Flows [113.4232528843775]
  We propose to model latent structures with a learned dynamic potential landscape. Inspired by physics, optimal transport, and neuroscience, these potential landscapes are learned as physically realistic partial differential equations. Our method achieves both more qualitatively and quantitatively disentangled trajectories than state-of-the-art baselines.
  arXiv  Detail & Related papers  (2023-04-25T15:53:45Z)
• Accurate and Robust Feature Importance Estimation under Distribution Shifts [49.58991359544005]
  PRoFILE is a novel feature importance estimation method. We show significant improvements over state-of-the-art approaches, both in terms of fidelity and robustness.
  arXiv  Detail & Related papers  (2020-09-30T05:29:01Z)
• Influence Functions in Deep Learning Are Fragile [52.31375893260445]
  influence functions approximate the effect of samples in test-time predictions. influence estimates are fairly accurate for shallow networks. Hessian regularization is important to get highquality influence estimates.
  arXiv  Detail & Related papers  (2020-06-25T18:25:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.