Constructing a Large-scale Landslide Database Across Heterogeneous Environments Using Task-Specific Model Updates
preprintposted on 2022-02-23, 04:34 authored by savinay nagendrasavinay nagendra, srikanth banagere manjunatha, daniel kifer, te pei, weixin li, kathryn lawson, hien nguyen, tong qiu, sarah tran, chaopeng shen
In this article, we consider the scenario where remotely sensed images are collected sequentially in temporal batches, where each batch focuses on images from a particular ecoregion, but different batches can focus on different ecoregions with distinct landscape characteristics. For such a scenario, we study the following questions: (1) How well do DL models trained in homogeneous regions perform when they are transferred to different ecoregions, (2) Does increasing the spatial coverage in the data improve model performance in a given ecoregion (even when the extra data do not come from the ecoregion), and (3) Can a landslide pixel labelling model be incrementally updated with new data, but without access to the old data and without losing performance on the old data (so that researchers can share models obtained from proprietary datasets)? We address these questions by a framework called Task-Specific Model Updates (TSMU). The goal of this framework is to continually update a (landslide) semantic segmentation model with data from new ecoregions without having to revisit data from old ecoregions and without losing performance on them. We conduct extensive experiments on four ecoregions in the United States to address the above questions and establish that data from other ecoregions can help improve the model's performance on the original ecoregion. In other words, if one has an ecoregion of interest, one could still collect data both inside and outside that region to improve model performance on the ecoregion of interest. Furthermore, if one has many ecoregions of interest, data from all of them are needed.