关键词: 生物多样性, 遥感监测, 昆明-蒙特利尔全球生物多样性框架, 人工智能

Abstract

Background: The Earth is approaching a critical tipping point of irreversible biodiversity loss. As the latest global action plan for biodiversity conservation, the Kunming-Montreal Global Biodiversity Framework (KMGBF) sets out 4 long-term goals and 23 action targets. Tracking and assessing progress toward the KMGBF has become a global concern. However, challenges such as unclear progress, untimely monitoring, and incomplete evaluations remain prominent, highlighting the urgent need to address technical barriers like a large number of evaluation indicators, inconsistent assessment standards, and weak data foundations. 

Aims: This study aims to explore rapid assessment methods for evaluating the implementation progress of the KMGBF using remote sensing monitoring. By integrating remote sensing-based and ground-based data, as well as combining quantitative and qualitative evaluations, this approach seeks to meet the multi-scale needs of quickly tracking the progress of the KMGBF. 

Problems & Prospects: This paper first points out that the existing monitoring frameworks exhibit significant uncertainties in effectively assessing the progress of the KMGBF. Therefore, it is necessary to develop a more operationally robust set of indicators, indicator calculation methods, and high-quality datasets with higher spatial resolution and more frequent updates to ensure the timely and effective tracking and assessment of the KMGBF. Second, this paper provides an in-depth analysis of the application of remote sensing technology in biodiversity monitoring and evaluates its feasibility in assessing the progress of the KMGBF. Based on this analysis, a spatial intelligence service framework integrating data, knowledge, and computation is proposed to support ecosystem mapping, biodiversity mapping, and the development of remote sensing-based essential biodiversity variables (RS-EBVs). Finally, this paper advocates for a quantitative assessment approach based on RS-EBVs, complemented by a qualitative assessment derived from National Biodiversity Strategies and Action Plans (NBSAPs) and National Reports (NRs). Additionally, it suggests leveraging artificial intelligence to develop an intelligent real-time monitoring system for the KMGBF, enabling rapid multi-scale progress assessments. These technological approaches aim to provide practical and feasible support for tracking the progress of the KMGBF and offer scientific evidence for countries to formulate and implement biodiversity conservation policies.

Key words: biodiversity, remote sensing monitoring, Kunming-Montreal Global Biodiversity Framework, artificial intelligence