| Abstrakt: |
Grassland is one of the most important resources for dairy farmers around the world. Deeper insights into the properties of grassland enable new applications. In particular, site-specific yield information is valuable for objective farm resource planning, fertilization, and field logistics. The Sentinel-2 satellites provide multi-spectral images with a spatial resolution of 10 × 10 m. According to recent studies, these satellite data are successfully used to predict the yield of arable crops. The biggest challenges for satellite data in the visible and near-infrared spectrum are atmospheric disturbances, such as clouds or fog. Current methods for approximating data between undisturbed satellite scans do not take weather data into account. We developed a novel approach to predict vegetation indices such as NDVI, EVI, NDWI, LAI, and FAPAR using multispectral satellite and weather data. Based on this model, transfer learning was introduced to train a grassland yield model. We compared artificial neural network architectures for predicting vegetation indices and grassland yields, including a multi-task formulation to additionally classify the crop types. The training samples for biomass prediction (n = 292) were collected in 2021. The crop prediction in the grassland crop category has an accuracy of 47.6%. The prediction of the vegetation indices and rgb values for three different time periods, ranging from 0 to 20 days after the last satellite scan, was done. The prediction of the leaf area index, for example, achieves a Pearson correlation of r = 0.904 and a mean absolute error (mae) of 0.324 m 2 m 2 for the period from 10 to 20 days from the latest satellite image. Finally, the Pearson correlation of the grassland fresh mass yield prediction was r = 0.891 with m a e = 1.245 kg m 2. [ABSTRACT FROM AUTHOR] |
Full text from SpringerLink