Deriving moderate spatial resolution leaf area index estimates from coarser spatial resolution satellite products

Leaf Area Index (LAI) is a key parameter used to characterize vegetation biophysical properties and plays an important regulatory role in terrestrial-atmospheric exchanges. Subsequently, LAI is often a critical data input to various evapotranspiration, hydrological and climatic models. While LAI data can generally be easily obtained, it is seldom available at spatio-temporal scales that can be used to guide and inform management decisions for localised applications. To this end, we propose a methodology to acquire moderate resolution LAI (LAIMR) estimates from freely available satellite-earth observation data sets and data processing platforms. Fifteen sites distributed within the KwaZulu-Natal and Mpumalanga provinces of South Africa were selected as study areas. Coarse spatial resolution MODIS LAI and vegetation index (VI) products were acquired for each of these sites to establish the LAI-VI relationship which was then used to develop machine learning-based models (MLBMs) to estimate LAIMR using VIs derived from Landsat or Sentinel-2 data. During the validation and testing phases of the study, LAI estimates were compared against the corresponding MODIS LAI product values. The results of these investigations demonstrated that MLBMs performed satisfactorily across the majority of the study sites, producing correlation coefficients ranging from 0.62 to 0.97 and 0.29-0.84 for the validation and testing phases, respectively. The poorer performance of the MLBMs when using VIs derived from Landsat or Sentinel-2 data can be largely attributed to inherent limitations associated with the proposed methodology, such as i) the lack of moderate-high spatial resolution LAI records that could be used for training and testing purposes and ii) saturation effects associated with the use of VIs. Notwithstanding these limitations, the proposed methodology has been shown to be flexible and robust and can be a useful approach to acquire LAIMR estimates with fairly reasonable accuracy in data limited circumstances.