Integrated Approach for Tree Health Prediction in Reforestation Using Satellite Data and Meteorological Parameters

Effective management of reforestation projects faces the challenges posed by deforestation and evolving environmental conditions, necessitating accurate tree health monitoring.

This study introduces a holistic methodology that synergizes high-resolution satellite imagery from Planet and historical data from Sentinel 2 with meteorological insights extracted from ERA5 data. By computing vital vegetation indices (NDVI, NDWI, mSAVI2) and meteorological indices (SPI, KBDI), we establish customized growing conditions, enabling the prediction and continuous monitoring of tree health and stress. The approach integrates time series models for temperature, precipitation, and vegetation indices, augmenting the understanding of growing conditions and facilitating informed site selection for reforestation initiatives. Satellite data is sourced from Copernicus (Sentinel 2 using GEE) and Planet imagery (via QGIS plugin). Copernicus Climate Data Store (ERA5) provides meteorological and climate assimilation data, complemented by reforestation specifics such as tree counts and planting timelines.

Our workflow involves data preparation, including the computation of vegetation and meteorological indices. The process follows several logical steps, which are either done sequentially or (where possible) in parallel. First, by using Facebook Prophet, a baseline reference is constructed starting from 2017, aiding in subsequent automatic forecasting. This baseline is used to compare the predicted NDVI against location-specific averages to gain insights into vegetation dynamics across multiple time frames. Utilizing Planet-NICFI monthly surface reflectance, we aggregate vegetation indices into a 100m grid, facilitating effective site comparisons. NDVI, NDWI, and mSAVI2 contribute to multi-dimensional vegetation assessment, detecting robust vegetation cover, optimal moisture levels, and early crop stages, respectively.

ERA5 temperature and precipitation data are downscaled to derive KBDI and SPI indices, enhancing our understanding of drought severity and precipitation patterns. Time series models, employing the Facebook Prophet library, forecast temperature and precipitation trends at specific sites, enabling the anticipation of future weather-driven indices.

Results demonstrate a versatile framework for regional forecasting adaptable to diverse scenarios. By leveraging the predictive power of NDVI, temperature, and precipitation, we effectively forecast NDVI six months ahead. This predictive capability empowers informed decision-making in reforestation, agriculture, and land management. The integrated approach presents a user-friendly means for stakeholders to gauge tree health and stress, contributing to targeted and sustainable environmental interventions.

In conclusion, this study showcases the potential of integrated satellite imagery and meteorological data for accurate tree health prediction in reforestation endeavours. Our approach emphasizes the value of data synergy and predictive modelling, offering promise for advancing sustainable reforestation practices and promoting ecological resilience.