Search

Abstract: Essential climate variables such as LAI or FAPAR are required for the monitoring, understanding and modeling of land surfaces at the global scale. While several products were already developed from the current medium resolution sensors, the few validation exercises currently achieved highlighted significant discrepancies and inconsistencies. The objective of this study is to develop improved global estimates of LAI, FAPAR and FCOVER variables by capitalizing on the development and validation of already existing products. In a first step, the performances of the MODIS, CYCLOPES, GLOBCARBON and JRC-FAPAR products were reviewed. The MODIS and CYCLOPES products were then selected since they provide higher level of consistency. These products were fused to generate the improved LAI, FAPAR and FCOVER values that were later scaled to closely match their expected range of variation. Finally, neural networks were trained to estimate these fused and scaled products from SPOT-VEGETATION top of canopy directionally normalized reflectance values. The resulting GEOV1 products are associated to quality control flags as well as quantitative estimates of uncertainties. Performances of the GEOV1 products are finally evaluated in a companion paper. The GEOV1 products are freely available to the community at www.geoland2.eu from 1999 up to present, globally at 1/112° spatial sampling grid at the dekadal time step. [Copyright &y& Elsevier]

Abstract: This paper evaluates the performances of a neural network approach to estimate LAI from CYCLOPES and MODIS nadir normalized reflectance and LAI products. A data base was generated from these products over the BELMANIP sites during the 2001–2003 period. Data were aggregated at 3 km×3 km, resampled at 1/16 days temporal frequency and filtered to reject outliers. VEGETATION and MODIS reflectances show very consistent values in the red, near infrared and short wave infrared bands. Neural networks were trained over part of this data base for each of the 6 MODIS biome classes to retrieve both MODIS and CYCLOPES LAI products. Results show very good performances of neural networks to estimate the original LAI products with an overall root mean square error (RMSE) around 0.5 for MODIS LAI from both MODIS and CYCLOPES normalized reflectances and a RMSE ranging between 0.12 (CYCLOPES reflectances) and 0.29 (MODIS reflectances) for CYCLOPES LAI. A drop of 15% of performance was found by training MODIS biome dependant algorithm by a single network over all the classes at the same time. More detailed analyses show that CYCLOPES and MODIS LAI values are very consistent for grasses and crops. Conversely, other biomes including shrubs, savanna, needleleaf and broadleaf forests show significant discrepancies, mainly due to differences between LAI definitions used between CYCLOPES (closer to effective LAI) and MODIS (closer to true LAI). However, products derived from the original CYCLOPES LAI products show a better agreement with both effective and true LAI ground measurements values. MODIS LAI products show more instability, partly because of the slightly shorter temporal resolution as compared to CYCLOPES. These results confirm the interest and versatility of neural networks for operational algorithms. This approach could be extended to other products or sensors, and may constitute a step forward for the fusion of data from several sensors, hence contributing to develop ‘virtual constellations’. [Copyright &y& Elsevier]

Abstract: A neural network is developed to operationally estimate biophysical variables over land surfaces from the observations of the ENVISAT-MERIS instrument: the leaf area index (LAI), the fraction of absorbed photosynthetically active radiation (fAPAR), the fraction of vegetation cover (fCover), and the canopy chlorophyll content (LAI×C ab ). The neural network requires as input the geometry of observation and the top of canopy reflectances, corrected from the atmospheric effects, in eleven spectral bands. It is trained on a reflectance database made of radiative transfer model simulations. The principles underlying the generation of the database and the design of the network are first presented. The estimated variables are then compared to other existing products, LAI- and fAPAR-MODIS and MGVI-MERIS, and validated against ground measurements performed in the framework of the VALERI project. Results show remarkable consistency of the temporal dynamics between the several products with however some differences in the range of variation. When compared to actual VALERI ground measurements, the proposed algorithm shows the best performances for LAI (RMSE=0.47) and fAPAR (RMSE=0.09). [Copyright &y& Elsevier]

This paper outlines the strategies available for estimating the biophysical properties of crop canopies from remotely sensed data. Spectral reflectance and biophysical data were obtained over 132 plots of sugar beet ( Beta vulgaris L.) and in the first part of the paper the strength of the relationships between vegetation indices (VI) and leaf area index (LAI) are examined. In the second part, an approach is tested in which a canopy reflectance model is used to generate simulated spectra for a wide range of biophysical conditions and these data are used to train an artificial neural network (ANN). The advantage of the second approach is that a priori knowledge of the measurement conditions including soil reflectance, canopy architecture and solar position can be included explicitly in the modelling. The results show that the estimation of sugar beet LAI using a trained neural network is more reliable than the use of VI and has the potential to replace the use of VI for operational applications. The use of a priori data on the variation in soil spectral reflectance gave rise to a small increase in LAI estimation accuracy. [ABSTRACT FROM AUTHOR]

Estimation of canopy biophysical variables from remote sensing data was investigated using radiative transfer model inversion. Measurement and model uncertainties make the inverse problem ill posed, inducing difficulties and inaccuracies in the search for the solution. This study focuses on the use of prior information to reduce the uncertainties associated to the estimation of canopy biophysical variables in the radiative transfer model inversion process. For this purpose, lookup table (LUT), quasi-Newton algorithm (QNT), and neural network (NNT) inversion techniques were adapted to account for prior information. Results were evaluated over simulated reflectance data sets that allow a detailed analysis of the effect of measurement and model uncertainties. Results demonstrate that the use of prior information significantly improves canopy biophysical variables estimation. LUT and QNT are sensitive to model uncertainties. Conversely, NNT techniques are generally less accurate. However, in our conditions, its accuracy is little dependent significantly on modeling or measurement error. We also observed that bias in the reflectance measurements due to miscalibration did not impact very much the accuracy of biophysical estimation. [Copyright &y& Elsevier]

Wide field view (WFV) sensor on board the Chinese GF-1, the first satellite of the China High-resolution Earth Observation System, is acquiring multi-spectral data with decametric spatial resolution, high temporal resolution and wide coverage, which are valuable data sources for environment monitoring. The objective of this study is to develop a general and reliable fractional vegetation cover (FVC) estimation algorithm for GF-1 WFV data under various land surface conditions. The algorithm is expected to estimate FVC from GF-1 WFV reflectance data with spatial resolution of 16 m and temporal resolution of four dates. The proposed algorithm is based on training back propagation neural networks (NNs) using PROSPECT + SAIL radiative transfer model simulations for GF-1 WFV canopy reflectance and corresponding FVC values. Green, red and near-infrared bands' reflectances of GF-1 WFV data are the input variables of the NNs, as well as the corresponding FVC is the output variable, and finally 842,400 simulated samples covering various land surface conditions are used for training the NNs. A case study in Weichang County of China, having abundant land cover types, was conducted to validate the performance of the proposed FVC estimation algorithm for GF-1 WFV data. The validation results showed that the proposed algorithm worked effectively and generated reasonable FVC estimates with R 2 = 0.790 and root mean square error of 0.073 based on the field survey data. The proposed algorithm can be operated without prior knowledge on the land cover and has the potential for routine production of high quality FVC products using GF-1 WFV surface reflectance data. [ABSTRACT FROM AUTHOR]