Satellite canopy water content from Sentinel-2, Landsat-8 and MODIS: Principle, algorithm and assessment

Abstract

In spite of the efforts made for canopy water content (CWC) mapping in the community, including vegetation water proxy from microwave-based vegetation optical depth (VOD) as well as optical-based indices, there is still no operational CWC product from optical satellites up to now. To fill this gap, this study proposes a unified algorithm for CWC mapping at both decametric and coarse spatial resolution from several widely used optical satellites. Based on machine learning trained on radiative transfer model simulations, we comprehensively parameterized the distribution of the canopy and vegetation input variables (i.e., leaf traits and soil background) of the PROSAIL model, by relying on the largest open integrated global plant and soil spectral databases. We investigated the impact of diverse band combinations as well as the inclusion of optical indices for CWC estimation using RTMs. The performances of this algorithm were first evaluated at decametric resolution based on ground measurements distributed over five ground campaigns corresponding to diverse climate and biome types. The retrieved CWC from Sentinel-2 and Landsat-8 exhibits satisfactory performance, with coefficient R of 0.81 and RMSE of 0.046 g/cm². We then evaluated CWC at 500 m resolution from MODIS by comparing it with Landsat-8 and Sentinel-2 aggregated values over a globally distributed selection of LANDVAL sites, representative of the existing biome types combined with a range of precipitation, soil moisture and vegetation density conditions. The MODIS CWC global maps show reasonable seasonal and spatial patterns compared to multi-frequencies microwave-based VOD, and improvements compared to the conventionally and extensively used optical indices such as NDWI. The CWC product developed in this study is expected to provide new insights for global or regional vegetation water variations monitoring from optical satellites, with the strength of high spatial resolution compared to the microwave passive VOD (i.e., 20-500 m vs 22.5 km). These two products could be further combined for more accurate global vegetation water and biomass mapping in the future to improve our understanding of carbon uptake and hydrological applications.

Plant phenotyping relevance

光学衛星画像から植物群落の含水量（CWC）を推定する統合アルゴリズムを開発し、複数の衛星・地上測定で性能評価しているため、植物形質推定法が中心である。

Code and data availability

公開状態または取得可能な本文経路を確認できませんでした。

No evidence-backed public reproduction asset is currently recorded.