From local spectral measurements to maps of vegetation cover and biomass on the Qinghai-Tibet-Plateau: Do we need hyperspectral information?

- Over 1100 hyperspectral measurements, vegetation cover and biomass (AGB) records.
- Random Forests based hyper- and multispectral estimation of vegetation cover and AGB.
- Multispectral information is sufficient to estimate vegetation cover and AGB.
- Regionalization of vegetation cover and AGB using 7 high resolution satellite scenes.
- The results will help to monitor pasture degradation on the Qinghai-Tibet Plateau.

Though the relevance of pasture degradation on the Qinghai-Tibet Plateau (QTP) is widely postulated, its extent is still unknown. Due to the enormous spatial extent, remote sensing provides the only possibility to investigate pasture degradation via frequently used proxies such as vegetation cover and aboveground biomass (AGB). However, unified remote sensing approaches are still lacking. This study tests the applicability of hyper- and multispectral in situ measurements to map vegetation cover and AGB on regional scales. Using machine learning techniques, it is tested whether the full hyperspectral information is needed or if multispectral information is sufficient to accurately estimate pasture degradation proxies. To regionalize pasture degradation proxies, the transferability of the locally derived ML-models to high resolution multispectral satellite data is assessed. 1183 hyperspectral measurements and vegetation records were performed at 18 locations on the QTP. Random Forests models with recursive feature selection were trained to estimate vegetation cover and AGB using narrow-band indices (NBI) as predictors. Separate models were calculated using NBI from hyperspectral data as well as from the same data resampled to WorldView-2, QuickBird and RapidEye channels. The hyperspectral results were compared to the multispectral results. Finally, the models were applied to satellite data to map vegetation cover and AGB on a regional scale. Vegetation cover was accurately predicted by Random Forest if hyperspectral measurements were used (cross validated R2 = 0.89). In contrast, errors in AGB estimations were considerably higher (cross validated R2 = 0.32). Only small differences in accuracy were observed between the models based on hyperspectral compared to multispectral data. The application of the models to satellite images generally resulted in an increase of the estimation error. Though this reflects the challenge of applying in situ measurements to satellite data, the results still show a high potential to map pasture degradation proxies on the QTP. Thus, this study presents robust methodology to remotely detect and monitor pasture degradation at high spatial resolutions.