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

TL;DR

This paper presents a model-agnostic explainability pipeline for spatiotemporal land surface forecasting models, combining perturbation and global explainability techniques to analyze complex satellite-based climate models.

Contribution

It introduces a novel explainability pipeline that simplifies analysis of high-dimensional spatiotemporal models, integrating perturbation and marginal explainability methods.

Findings

Precipitation has the highest sensitivity on NDVI in the study area.

Temperature and pressure also influence NDVI, with pressure showing minimal effect.

Nonlinear correlations between meteorological variables and NDVI were discovered.

Abstract

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.