Forecasting localized weather impacts on vegetation as seen from space with meteo-guided video prediction

Benson, Vitus; Requena-Mesa, Christian; Robin, Claire Nicolle; Alonso, Lazaro; Cortés, José Luis; Gao, Zeyu; Linscheid, Nora; Weynants, Mélanie; Reichstein, Markus

doi:10.48550/arxiv.2303.16198

Cited by 3 publications

(4 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar to previous investigations (Benson et al, 2023) sites, as illustrated in Fig. A1, and can explain the overlap in the standard deviation.…”

Section: Model's Performance and Comparisonsupporting

confidence: 91%

“…However, these models exhibited limited predictive capability for extreme events. Spatial information has proven helpful in similar investigations (Requena-Mesa et al, 2021;Diaconu et al, 2022;Kladny et al, 2022;Robin et al, 2022;Benson et al, 2023) and it could be beneficial to explore the extent to which it contributes to extreme conditions. Furthermore, the models used could be tailored more to the task.…”

Section: Limitation and Future Directionsmentioning

confidence: 99%

See 1 more Smart Citation

Learning Extreme Vegetation Response to Climate Forcing: A Comparison of Recurrent Neural Network Architectures

Martinuzzi,

Mahecha,

Camps-Valls

et al. 2023

Preprint

View full text Add to dashboard Cite

Abstract. Vegetation state variables are key indicators of land-atmosphere interactions characterized by long-term trends, seasonal fluctuations, and responses to weather anomalies. This study investigates the potential of neural networks in capturing vegetation state responses, including extreme behavior driven by atmospheric conditions. While machine learning methods, particularly neural networks, have significantly advanced in modeling nonlinear dynamics, it has become standard practice to approach the problem using recurrent architectures capable of capturing nonlinear effects and accommodating both long and short-term memory. We compare four recurrence-based learning models, which differ in their training and architecture: 1) recurrent neural networks (RNNs), 2) long short-term memory-based networks (LSTMs), 3) gated recurrent unit-based networks (GRUs), and 4) echo state networks (ESNs). While our results show minimal quantitative differences in their performances, ESNs exhibit slightly superior results across various metrics. Overall, we show that recurrent network architectures prove generally suitable for vegetation state prediction yet exhibit limitations under extreme conditions. This study highlights the potential of recurrent network architectures for vegetation state prediction, emphasizing the need for further research to address limitations in modeling extreme conditions within ecosystem dynamics.

show abstract

“…Similar to previous investigations (Benson et al, 2023) sites, as illustrated in Fig. A1, and can explain the overlap in the standard deviation.…”

Section: Model's Performance and Comparisonsupporting

confidence: 91%

Section: Limitation and Future Directionsmentioning

confidence: 99%

Learning Extreme Vegetation Response to Climate Forcing: A Comparison of Recurrent Neural Network Architectures

Martinuzzi,

Mahecha,

Camps-Valls

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…In their framework, vegetation dynamics approximated by NDVI is modeled at high resolution using past satellite images as initial conditions and static and reanalysis data as a model guidance. Similar approaches with this framework were presented in (Robin et al, 2022;Kladny et al, 2022;Diaconu et al, 2022) and on a continental-scale in (Benson et al, 2023). While these works differ in their methodologies, i.e.…”

Section: Vegetation Health Predictionmentioning

confidence: 81%

Focal-TSMP: Deep learning for vegetation health prediction and agricultural drought assessment from a regional climate simulation

Shams Eddin,

Gall

2023

Preprint

View full text Add to dashboard Cite

Abstract. In this study, we investigate applying deep learning (DL) models on a regional climate simulation produced by the Terrestrial Systems Modelling Platform (TSMP Ground to Atmosphere G2A) for vegetation health modeling and agricultural drought assessment. The TSMP simulation is performed in a free mode and the DL model is used in an intermediate step to synthesize Normalized Difference Vegetation Index (NDVI) and Brightness Temperature (BT) images from the TSMP simulation over Europe. These predicted images are then used to derive different vegetation and drought indices like NDVI anomaly, BT anomaly, Vegetation Condition Index (VCI), Thermal Condition Index (TCI), and Vegetation Health Index (VHI). To ensure reliability and to assess the model applicability with different seasonality and spatial variability, we provide an analysis of model biases and uncertainties across different regions over the Pan-Europe domain. We further provide an analysis about the contribution of the input variables from the TSMP model components to ensure a better understanding of the model prediction. A comprehensive evaluation on the long-term TSMP using reference remote sensing data showed sufficiently good agreements between the model predictions and observations. While model performance varies on the test set between different climate regions, it achieves a mean absolute error (MAE) of 0.027 and 1.90 K° with coefficient of determination (R2) scores of 0.88 and 0.92 for NDVI and BT, respectively, at 0.11° resolution for sub-seasonal predictions. Our study could be used as a complimentary evaluation framework for climate change simulations with TSMP. Moreover, the developed DL model could be integrated with data assimilation and used for down-stream tasks, i.e., modelling the impact of extreme events on vegetation responses with different climate change scenarios. In summary, we demonstrate the feasibility of using DL on a TSMP simulation to synthesize NDVI and BT, which can be used for agricultural drought forecasting. Our implementation is publicly available at the project page (https://hakamshams.github.io/Focal-TSMP).

show abstract

“…With the onset of Artificial Intelligence (AI), the rich EO archive can be further exploited to seamlessly monitor environmental variables and disaster impacts towards forecasting natural disasters, for example droughts [30], wildfires [31] and volcanic unrest [32]. Linking anticipated disasters with migration flows is a non-trivial task.…”

Section: Earth Observation and Causalitymentioning

confidence: 99%

Earth observation as a tool to assess climate migration and policy-making: Legal aspects

Koskina,

Plionis,

Papoutsis

et al. 2023

E3S Web Conf.

View full text Add to dashboard Cite

The impact of climate change on the biosphere and atmosphere is well documented but its impact on the anthroposphere needs to be better understood. Indeed, divergent views remain both at the regional level -as shown by (i) the EU case-by-case approach (ii) the African Kampala Convention (2009) and (iii) the Latin-American Lineamientos regionales (2018)- and finally the international one. As the Paris Agreement (2015) urges States to use best available scientific knowledge to counter the negative effects of climate change, we argue that Earth Observation (EO) could be potentially exploited by policy-makers as an efficient platform for modeling, forecasting, characterizing and understanding the severity of migration flows, contributing to evidence-based Anticipatory Action (A-A) for the effective management of climate migration, and setting the direction for future policies in this field that would be equitable on both regional and international scales. Hence, in implementing the Paris Agreement, States should increase the funding and use of EO and Causality as policy-supporting tools, to reduce the need for reactive and costly responses to displacement, and promote the safety, dignity, and well-being of people affected by climate change. However, based on said input, a well-adapted framework for the legal protection of climate migrants should be adopted.

show abstract

Forecasting localized weather impacts on vegetation as seen from space with meteo-guided video prediction

Cited by 3 publications

References 41 publications

Learning Extreme Vegetation Response to Climate Forcing: A Comparison of Recurrent Neural Network Architectures

Learning Extreme Vegetation Response to Climate Forcing: A Comparison of Recurrent Neural Network Architectures

Focal-TSMP: Deep learning for vegetation health prediction and agricultural drought assessment from a regional climate simulation

Earth observation as a tool to assess climate migration and policy-making: Legal aspects

Contact Info

Product

Resources

About