paper-with-me

Papers

Cluster-Segregate-Perturb (CSP): A Model-agnostic Explainability Pipeline for Spatiotemporal Land Surface Forecasting Models

2024-08-12 · Tushar Verma, Sudipan Saha

Satellite images have become increasingly valuable for modelling regional climate change effects. Earth surface forecasting represents one such task that integrates satellite images with meteorological data to capture the joint evolution of regional climate change effects. However, understanding the complex relationship between specific meteorological variables and land surface evolution poses a significant challenge. In light of this challenge, our paper introduces a pipeline that integrates principles from both perturbation-based explainability techniques like LIME and global marginal explainability techniques like PDP, besides addressing the constraints of using such techniques when applying them to high-dimensional spatiotemporal deep models. The proposed pipeline simplifies the undertaking of diverse investigative analyses, such as marginal sensitivity analysis, marginal correlation analysis, lag analysis, etc., on complex land surface forecasting models In this study we utilised Convolutional Long Short-Term Memory (ConvLSTM) as the surface forecasting model and did analyses on the Normalized Difference Vegetation Index (NDVI) of the surface forecasts, since meteorological variables like temperature, pressure, and precipitation significantly influence it. The study area encompasses various regions in Europe. Our analyses show that precipitation exhibits the highest sensitivity in the study area, followed by temperature and pressure. Pressure has little to no direct effect on NDVI. Additionally, interesting nonlinear correlations between meteorological variables and NDVI have been uncovered.

📄 PDF Abstract BibTeX arXiv:2408.05916

Code (0)

등록된 구현이 없습니다.

Tasks

Earth Surface ForecastingSensitivity

Methods 이 논문이 사용한 방법론

LIME LIME, or Local Interpretable Model-Agnostic Explanations, is an algorithm that can explain the predictions of any classifier or regressor in a faithful way, by…

Similar Papers 제목 키워드 기반

Algorithm-Agnostic Explainability for Unsupervised Clustering

2021-05-17 · Charles A. Ellis, Mohammad S. E. Sendi, Eloy P. T. Geenjaar, Sergey M. Plis 외

Supervised machine learning explainability has developed rapidly in recent years. However, clustering explainability has lagged behind. Here, we demonstrate the first adaptation of model-agnostic explainability methods t…

BIG-bench Machine LearningClusteringExplainable artificial intelligenceFeature Importance

Explaining AutoClustering: Uncovering Meta-Feature Contribution in AutoML for Clustering

2026-02-20 · Matheus Camilo da Silva, Leonardo Arrighi, Ana Carolina Lorena, Sylvio Barbon Junior arxiv

AutoClustering methods aim to automate unsupervised learning tasks, including algorithm selection (AS), hyperparameter optimization (HPO), and pipeline synthesis (PS), by often leveraging meta-learning over dataset meta-…

Hyperparameter OptimizationFeature EngineeringFeature Importance

GALACTIC: Global and Local Agnostic Counterfactuals for Time-series Clustering

2026-03-05 · Christos Fragkathoulas, Eleni Psaroudaki, Themis Palpanas, Evaggelia Pitoura arxiv

Time-series clustering is a fundamental tool for pattern discovery, yet existing explainability methods, primarily based on feature attribution or metadata, fail to identify the transitions that move an instance across c…

DLIME: A Deterministic Local Interpretable Model-Agnostic Explanations Approach for Computer-Aided Diagnosis Systems

2019-06-24 · Muhammad Rehman Zafar, Naimul Mefraz Khan

Local Interpretable Model-Agnostic Explanations (LIME) is a popular technique used to increase the interpretability and explainability of black box Machine Learning (ML) algorithms. LIME typically generates an explanatio…

ClusteringFeature Importancefeature selection

Evaluating Black-Box Vulnerabilities with Wasserstein-Constrained Data Perturbations

2026-03-16 · Adriana Laurindo Monteiro, Jean-Michel Loubes arxiv

The growing use of Machine Learning (ML) tools comes with critical challenges, such as limited model explainability. We propose a global explainability framework that leverages Optimal Transport and Distributionally Robu…