Quantifying Heterogeneous Ecosystem Services With Multi-Label Soft Classification

TL;DR

It is demonstrated how land use proxy labels can be implemented with a soft, multi-label classifier to predict ecosystem services with complex heterogeneity.

Abstract

Understanding and quantifying ecosystem services are crucial for sustainable environmental management, conservation efforts, and policy-making. The advancement of remote sensing technology and machine learning techniques has greatly facilitated this process. Yet, ground truth labels, such as biodiversity, are very difficult and expensive to measure. In addition, more easily obtainable proxy labels, such as land use, often fail to capture the complex heterogeneity of the ecosystem. In this paper, we demonstrate how land use proxy labels can be implemented with a soft, multi-label classifier to predict ecosystem services with complex heterogeneity.

Figures (11)

• Figure 1: Processing pipeline for quantifying ecosystem services
• Figure 2: The fully connected layer used to translate the land use proxy variable into ecosystem service scores.
• Figure 3: Illustration of the training data (left) and testing data (right) used in predicting ecosystem services scores of Alachua County in Florida, USA.
• Figure 5: Groundwater recharge score histogram for the three classifiers considered
• Figure : (a) Biodiversity object-based hard classification