Learning to forecast vegetation greenness at fine resolution over Africa with ConvLSTMs
Learning to forecast vegetation greenness at fine resolution over Africa with ConvLSTMs
复制标题
学习使用 ConvLSTM 以高分辨率预测非洲植被绿度
DOI：
--
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
M. Reichstein
中科院分区：
文献类型：
--
作者：
Claire Robin;C. Requena;V. Benson;Lazaro Alonso;Jeran Poehls;N. Carvalhais;M. Reichstein
根据气候和天气事件预测植被状况是一项重大挑战。它的实施将证明对预测作物产量、森林破坏或更一般地对与社会经济运作有关的生态系统服务的影响至关重要，如果不实施，可能导致人道主义灾难。植被状况取决于天气和环境条件，这些条件调节着在几个时间尺度上发生的复杂生态过程。植被和不同的环境驱动因素之间的相互作用表达的反应在瞬间，但也有时滞效应，往往显示出一个新兴的景观和区域尺度的空间背景。我们制定的陆面预测任务作为一个强有力的指导视频预测任务，其目标是预测植被发展在非常精细的分辨率，使用地形和天气变量来指导预测。我们使用卷积LSTM（ConvLSTM）架构来解决这一任务，并使用Sentinel-2卫星NDVI预测非洲植被状态的变化，将ERA 5天气再分析，SMAP卫星测量和地形（SRTMv4.1的DEM）作为变量来指导预测。我们的研究结果突出了ConvLSTM模型不仅可以高分辨率预测NDVI的季节演变，还可以预测天气异常对基线的差异影响。该模型能够预测不同的植被类型，甚至是在目标长度内归一化差异植被指数变异性很高的植被类型，这有望支持在与干旱有关的灾害中采取预期行动。
Forecasting the state of vegetation in response to climate and weather events is a major challenge. Its implementation will prove crucial in predicting crop yield, forest damage, or more generally the impact on ecosystems services relevant for socio-economic functioning, which if absent can lead to humanitarian disasters. Vegetation status depends on weather and environmental conditions that modulate complex ecological processes taking place at several timescales. Interactions between vegetation and different environmental drivers express responses at instantaneous but also time-lagged effects, often showing an emerging spatial context at landscape and regional scales. We formulate the land surface forecasting task as a strongly guided video prediction task where the objective is to forecast the vegetation developing at very fine resolution using topography and weather variables to guide the prediction. We use a Convolutional LSTM (ConvLSTM) architecture to address this task and predict changes in the vegetation state in Africa using Sentinel-2 satellite NDVI, having ERA5 weather reanalysis, SMAP satellite measurements, and topography (DEM of SRTMv4.1) as variables to guide the prediction. Ours results highlight how ConvLSTM models can not only forecast the seasonal evolution of NDVI at high resolution, but also the differential impacts of weather anomalies over the baselines. The model is able to predict different vegetation types, even those with very high NDVI variability during target length, which is promising to support anticipatory actions in the context of drought-related disasters.