Work

Ai4Fapar: How artificial intelligence can help to forecast the seasonal earth observation signal

Year: 2023

Type: conference-paper

Abstract: Leaf Area Index (LAI) is a key parameter in crop growth models, and its accurate estimation is crucial for yield prediction. However, LAI data values are often missing or incomplete due to various reasons, such as sensor failures or cloud cover. In this paper, we propose a set of time series data imputation methods for LAI values derived from satellite images by radiative transfer model (RTM) inversion. The methods perform temporal interpolation either at the level of individual pixels or on spatial aggregates. Our experimental evaluation demonstrates that our approach can be applied to various crop types and has the potential to improve the accuracy and timeliness of yield prediction.

Source: TU/e Research Portal

DOI: 10.2760/46796