Search

Land cover maps obtained at high spatial and temporal resolutions are necessary to support monitoring and management applications in areas with many smallholder and low-input agricultural systems, as those characteristic in Mozambique. Various regional and global land cover products based on Earth Observation data have been developed and made publicly available but their application in regions characterized by a large variety of agro-systems with a dynamic nature is limited by several constraints. Challenges in the classification of spatially heterogeneous landscapes, as in Mozambique, include the definition of the adequate spatial resolution and data input combinations for accurately mapping land cover. Therefore, several combinations of variables were tested for their suitability as input for random forest ensemble classifier aimed at mapping the spatial dynamics of smallholder agricultural landscape in Vilankulo district in Mozambique. The variables comprised spectral bands from Landsat 7 ETM+ and Landsat 8 OLI/TIRS, vegetation indices and textural features and the classification was performed within the Google Earth Engine cloud computing for the years 2012, 2015, and 2018. The study of three different years aimed at evaluating the temporal dynamics of the landscape, typically characterized by high shifting nature. For the three years, the best performing variables included three selected spectral bands and textural features extracted using a window size of 25. The classification overall accuracy was 0.94 for the year 2012, 0.98 for 2015, and 0.89 for 2018, suggesting that the produced maps are reliable. In addition, the areal statistics of the class classified as agriculture were very similar to the ground truth data as reported by the Serviços Distritais de Actividades Económicas (SDAE), with an average percentage deviation below 10%. When comparing the three years studied, the natural vegetation classes are the predominant covers while the agriculture is the most important cause of land cover changes.

Several vegetation indices (VI) derived from handheld spectroradiometer reflectance data in the visible spectral region were tested for modelling grapevine water status estimated by the predawn leaf water potential (Ψpd). The experimental trial was carried out in a vineyard in Douro wine region, Portugal. A statistical approach was used to evaluate which VI and which combination of wavelengths per VI allows the best correlation between VIs and Ψpd. A linear regression was defined using a parameterization dataset. The correlation analysis between Ψpd and the VIs computed with the standard formulation showed relatively poor results, with values for squared Pearson correlation coefficient (r2) smaller than 0.67. However, the results of r2 highly improved for all VIs when computed with the selected best combination of wavelengths (optimal VIs). The optimal Visible Atmospherically Resistant Index (VARI) and Normalized Difference Greenness Vegetation Index (NDGI) showed the higher r2 and stability index results. The equations obtained through the regression between measured Ψpd (Ψpd_obs) and optimal VARI and between Ψpd_obs and optimal NDGI when using the parameterization dataset were adopted for predicting Ψpd using a testing dataset. The comparison of Ψpd_obs with Ψpd predicted based on VARI led to R2 = 0.79 and a regression coefficient b = 0.96. Similar R2 was achieved for the prediction based on NDGI, but b was smaller (b = 0.93). Results obtained allow the future use of optimal VARI and NDGI for estimating Ψpd, supporting vineyards irrigation management.

A new procedure is proposed for estimating actual basal crop coefficients from vegetation indices (Kcb VI) considering a density coefficient (Kd) and a crop coefficient for bare soil. Kd is computed using the fraction of ground cover by vegetation (fc VI), which is also estimated from vegetation indices derived from remote sensing. A combined approach for estimating actual crop coefficients from vegetation indices (Kc VI) is also proposed by integrating the Kcb VI with the soil evaporation coefficient (Ke) derived from the soil water balance model SIMDualKc. Results for maize, barley and an olive orchard have shown that the approaches for estimating both fc VI and Kcb VI compared well with results obtained using the SIMDualKc model after calibration with ground observation data. For the crops studied, the correlation coefficients relative to comparing the actual Kcb VI and Kc VI with actual Kcb and Kc obtained with SIMDualKc were larger than 0.73 and 0.71, respectively. The corresponding regression coefficients were close to 1.0. The methodology herein presented and discussed allowed for obtaining information for the whole crop season, including periods when vegetation cover is incomplete, as the initial and development stages. Results show that the proposed methods are adequate for supporting irrigation management.

Field spectra acquired from a handheld spectroradiometer and Sentinel-2 images spectra were used to investigate the applicability of hyperspectral and multispectral data in retrieving the maize leaf area index in low-input crop systems, with high spatial and intra-annual variability, and low yield, in southern Mozambique, during three years. Seventeen vegetation indices, comprising two and three band indices, and nine machine learning regression algorithms (MLRA) were tested for the statistical approach while five cost functions were tested in the look-up-table (LUT) inversion approach. The three band vegetation indices were selected, specifically the modified difference index (mDId: 725; 715; 565) for the hyperspectral dataset and the modified simple ratio (mSRc: 740; 705; 865) for the multispectral dataset of field spectra and the three band spectral index (TBSIb: 665; 865; 783) for the Sentinel-2 dataset. The relevant vector machine was the selected MLRA for the two datasets of field spectra (multispectral and hyperspectral) while the support vector machine was selected for the Sentinel-2 data. When using the LUT inversion technique, the minimum contrast estimation and the Bhattacharyya divergence cost functions were the best performing. The vegetation indices outperformed the other two approaches, with the TBSIb as the most accurate index (RMSE = 0.35). At the field scale, spectral data from Sentinel-2 can accurately retrieve the maize leaf area index in the study area.