A random forest model for the classification of wheat and rye leaf rust symptoms based on pure spectra at leaf scale

The pure spectra acquisition of plant disease symptoms is essential to improving the reliability of remote sensing methods in crop protection. The reflectance values read from the pure spectra can be used as valuable training data for development of algorithms designed for plant disease detection at leaf and canopy scale. The aim of this paper is to identify and distinguish spectrally the leaf rust symptoms caused by two closely related special forms (f. sp.) of Puccinia recondita f. sp. tritici on wheat and Puccinia recondita f. sp. recondita on rye at leaf scale. Spectral measurements were made with FieldSpec 3 spectrometer in the wavelength range of 350-2500 nm. The spectrometer was connected to a microscope by optical fiber. Raw spectra of uredinia, chlorotic discoloration, green leaves, senescent inoculated leaves and senescent uninoculated leaves of wheat and rye, all of which obtained for this study, were investigated with a view towards making an automized classification of plant species and their phases. The created Random Forest models were tested separately using pure spectra, and from these vegetation indices were derived as predictors. Three vegetation indices, namely CRI, PRI and GNDVI, appeared to be the most robust in terms of distinguishing uredinia from other symptoms on rye and wheat leaves. PRI, EVI, NDVI₇₀₅, and GNDVI were the most suitable for distinguishing uredinia, chlorotic discoloration, and green leaf stages on rye. That tusk on wheat leaves can be recognized if seven indices (PRI, MSAWI, SAVI, NDVI, NDVI₇₀₅, GNDVI and RVI) are used together. For the classification of all disease symptoms for both plant species, the most useful were wavelengths in the VIS range: 431-436, 696-703 and 646-686 nm. However, the ranges of SWIR wavelengths (1938, 1955) and NIR wavelengths (1099-1104) also have a high contribution to the discrimination accuracy of the model. In the classification of all disease symptoms, the most important vegetation indices were CRI, OSAVI, and GNDVI. Analysis of the results revealed the advantage of the model based on the selected spectral wavelengths (Hit Rate of 96.6%) in comparison with predictions based on vegetation indices alone (Hit Rate of 91.7%). Both approaches show the highly applicable character of utilizing high quality spectral products such as satellite images in reducing operational costs of crop protection.

High-resolution spectral information enables phenotyping of leaf epicuticular wax in wheat

BACKGROUND

Epicuticular wax (EW) is the first line of defense in plants for protection against biotic and abiotic factors in the environment. In wheat, EW is associated with resilience to heat and drought stress, however, the current limitations on phenotyping EW restrict the integration of this secondary trait into wheat breeding pipelines. In this study we evaluated the use of light reflectance as a proxy for EW load and developed an efficient indirect method for the selection of genotypes with high EW density.

RESULTS

Cuticular waxes affect the light that is reflected, absorbed and transmitted by plants. The narrow spectral regions statistically associated with EW overlap with bands linked to photosynthetic radiation (500 nm), carotenoid absorbance (400 nm) and water content (~ 900 nm) in plants. The narrow spectral indices developed predicted 65% (EWI-13) and 44% (EWI-1) of the variation in this trait utilizing single-leaf reflectance. However, the normalized difference indices EWI-4 and EWI-9 improved the phenotyping efficiency with canopy reflectance across all field experimental trials. Indirect selection for EW with EWI-4 and EWI-9 led to a selection efficiency of 70% compared to phenotyping with the chemical method. The regression model EWM-7 integrated eight narrow wavelengths and accurately predicted 71% of the variation in the EW load (mg·dm-2) with leaf reflectance, but under field conditions, a single-wavelength model consistently estimated EW with an average RMSE of 1.24 mg·dm-2 utilizing ground and aerial canopy reflectance.

CONCLUSIONS

Overall, the indices EWI-1, EWI-13 and the model EWM-7 are reliable tools for indirect selection for EW based on leaf reflectance, and the indices EWI-4, EWI-9 and the model EWM-1 are reliable for selection based on canopy reflectance. However, further research is needed to define how the background effects and geometry of the canopy impact the accuracy of these phenotyping methods.

Satellite imagery and machine learning for identification of aridity risk in central Java Indonesia

This study aims to develop a software framework for predicting aridity using vegetation indices (VI) from LANDSAT 8 OLI images. VI data are predicted using machine learning (ml): Random Forest (RF) and Correlation and Regression Trees (CART). Comparison of prediction using Artificial Neural Network (ANN), Support Vector Machine (SVM), k-nearest neighbors (k-nn) and Multivariate Adaptive Regression Spline (MARS). Prediction results are interpolated using Inverse Distance Weight (IDW). This study was conducted in stages: (1) Image preprocessing; (2) calculating numerical data extracted from the LANDSAT band imagery using vegetation indices; (3) analyzing correlation coefficients between VI; (4) prediction using RF and CART; (5) comparing performances between RF and CART using ANN, SVM, k-nn, and MARS; (6) testing the accuracy of prediction using Mean Square Error (MSE) and Mean Absolute Percentage Error (MAPE); (7) interpolating with IDW. Correlation coefficient of VI data shows a positive correlation, the lowest r (0.07) and the highest r (0.98). The experiments show that the RF and CART algorithms have efficiency and effectivity in determining the aridity areas better than the ANN, SVM, k-nn, and MARS algorithm. RF has a difference between the predicted results and 1.04% survey data MAPE and the smallest value close to zero is 0.05 MSE. CART has a difference between the predicted results and 1.05% survey data MAPE and the smallest value approaching to zero which is 0.05 MSE. The prediction results of VI show that in 2020 most of the study areas were low vegetation areas with the Normalized Difference Vegetation Index (NDVI) < 0.21, had an indication of drought with the Vegetation Health Index (VHI) < 31.10, had a Vegetation Condition Index (VCI) in some areas between 35%-50% (moderate drought) and < 35% (high drought). The Burn Area Index (dBAI) values are between -3, 971 and -2,376 that show the areas have a low fire risk, and index values are between -0, 208 and -0,412 that show the areas are starting vegetation growth. The result of this study shows that the machine learning algorithms is an accurate and stable algorithm in predicting the risks of drought and land fire based on the VI data extracted from the LANDSAT 8 OLL imagery. The VI data contain the record of vegetation condition and its environment, including humidity, temperatures, and the environmental vegetation health.

Estimating canopy nitrogen concentration of sugarcane crop using in situ spectroscopy

Estimating nitrogen (N) concentration in situ is fundamental for managing the fertilization of the sugarcane crop. The purpose of this work was to develop estimation models that explain how N varies over time as a function of three spectral data transformations in two stages (plant cane and first ratoon) under variable rates of N application. A randomized complete-block experimental design was applied, with four levels of N fertilization: 0, 80, 160, and 240 kg N ha⁻¹. Six sampling events were carried out during the rapid growth stage, where the canopy reflectance spectra with a hyperspectral sensor were measured, and tissue samples for N determination in plant cane and first ratoon were taken, from 60 days after emergence (DAE) and 60 days after harvest (DAH), respectively, until days 210 DAE and 210 DAH. To build the models, partial least squares regression analysis was used and was trained by three transformations of the spectral data: (i) average reflectance spectrum (R), (ii) multiple scatter correction and Savitzky-Golay filter MSC-SG) reflectance spectrum, and (iii) calculated vegetation indices (VIs).

Temporal record and spatial distribution of fire foci in State of Minas Gerais, Brazil

The objectives of this study are: (i) to evaluate the space-temporal variability of fire foci by environmental satellites, CHIRPS and remote sensing products based on applied statistics, and (ii) to identify the relational pattern between the distribution of fire foci and the environmental, meteorological, and socioeconomic variables in the mesoregions of Minas Gerais (MG) - Brazil. This study used a time series of fire foci from 1998 to 2015 via BDQueimadas. The temporal record of fire foci was evaluated by Mann-Kendall (MK), Pettitt (P), Shapiro-Wilk (SW), and Bartlett (B) tests. The spatial distribution by burned area (MCD64A1-MODIS) and the Kernel density - (radius 20 km) were estimated. The environmental variables analyzed were: rainfall (mm) and maximum temperature (°C), besides proxies to vegetation canopy: NDVI, SAVI, and EVI. PCA was applied to explain the interaction between fire foci and demographic, environmental, and geographical variables for MG. The MK test indicated a significant increasing trend in fire foci in MG. The SW and B tests were significant for non-normality and homogeneity of data. The P test pointed to abrupt changes in the 2001 and 2002 cycles (El Niño and La Niña moderated), which contributes to the annual increase and in winter and spring, which is identified by the Kernel density maps. Burned areas highlighted the northern and northwestern regions of MG, Triângulo Mineiro, Jequitinhonha, and South/Southwest MG, in the 3rd quarter (increased 17%) and the 4th quarter (increased 88%). The PCA resulted in three PCs that explained 71.49% of the total variation. The SAVI was the variable that stood out, with 11.12% of the total variation, followed by Belo Horizonte, the most representative in MG. We emphasize that the applied conceptual theoretical model defined here can act in the environmental management of fire risk. However, public policies should follow the technical-scientific guidelines in the mitigation of the resulting socioeconomic - environmental damages.

Extrapolating canopy phenology information using Sentinel-2 data and the Google Earth Engine platform to identify the optimal dates for remotely sensed image acquisition of semiarid mangroves

Continuum monitoring of mangrove ecosystems is required to maintain and improve upon national mangrove conservation strategies. In particular, mangrove canopy assessments using remote sensing methods can be undertaken rapidly and, if freely available, optimize costs. Although such spaceborne data have been used for such purposes, their application to map mangroves at the species level has been limited by the capacity to provide continuous data. The objective of this study was to assess mangrove seasonal patterns using seven multispectral vegetation indices based on a Sentinel-2 (S2) time series (July 2018 to October 2019) to assess phenological trajectories of various semiarid mangrove classes in the Google Earth Engine platform using Fourier analysis for an area located in Western Mexico. The results indicate that the months from November through December and from May through July were critical in mangrove species discrimination using the EVI2, NDVI, and VARI series. The Random Forest classification accuracy for the S2 image was calculated at 79% during the optimal acquisition period (June 25, 2019), whereas only 55% accuracy was calculated for the non-optimal image acquired date (March 2, 2019). Although mangroves are considered evergreen forests, the phenological pattern of various mangrove canopies, based on these indices, were shown to be very similar to the surrounding land-based semiarid deciduous forest. Consequently, it is believed that the rainfall pattern is likely to be the key environmental factor driving mangrove phenology in this semiarid coastal system and thus the degree of success in mangrove remote sensing classification endeavors. Identifying the optimal dates when canopy spectral conditions are ideal in achieving mangrove species discrimination could be of utmost importance when purchasing more expensive very-high spatial resolution satellite images or collecting spatial data from UAVs.

Combined MODIS land surface temperature and greenness data for modeling vegetation phenology, physiology, and gross primary production in terrestrial ecosystems

Vegetation phenology such as the start (SOS) and end (EOS) of the growing season, physiology (represented by seasonal maximum capacity of carbon uptake, GPPmax), and gross primary production (GPP) are sensitive indicators for monitoring ecosystem response to environmental change. However, uncertainty and disagreement between models limit the use phenology metrics and GPP derived from remote sensing data. Statistical models for estimating phenology and physiology were constructed based on key predictor variables derived from enhanced vegetation index (EVI) and land surface temperature (LST) data. Then, a statistical model that integrated remote sensing-based phenology and physiology (RS-SMIPP) data was constructed to estimate seasonal and annual GPP. These models were calibrated and validated with GPP observations from 512 site-years of FLUXNET data covering four plant functional types (PFTs) in the northern hemisphere: deciduous broadleaf forest, evergreen needle-leaf forest, mixed forest, and grassland. Our results showed that phenology and physiology were accurately estimated with relative root mean squared error (RMSEr) <20%, and the errors varied among the PFTs. Spring EVI was an important factor in explaining variation of GPPmax. The RS-SMIPP model outperformed the MOD17 algorithm in accurately estimating seasonal and annual GPP and reduced RMSEr from 25.34%-43.44% to 9.53%-26.19% for annual GPP of the different PFTs. These findings demonstrate that remote sensing-based phenological and physiological indicators could be used to explain the variations of seasonal and annual GPP, and provide an efficient way for improving GPP estimations at a global scale.

Estimation of leaf area index using PROSAIL based LUT inversion, MLRA-GPR and empirical models: Case study of tropical deciduous forest plantation, North India

Forests play a vital role in biological cycles and environmental regulation. To understand the key processes of forest canopies (e.g., photosynthesis, respiration and transpiration), reliable and accurate information on spatial variability of Leaf Area Index (LAI), and its seasonal dynamics is essential. In the present study, we assessed the performance of biophysical parameter (LAI) retrieval methods viz. Look-Up Table (LUT)-inversion, MLRA-GPR (Machine Learning Regression Algorithm-Gaussian Processes Regression) and empirical models, for estimating the LAI of tropical deciduous plantation using ARTMO (Automated Radiative Transfer Models Operator) tool and Sentinel-2 satellite images. The study was conducted in Central Tarai Forest Division, Haldwani, located in the Uttarakhand state, India. A total of 49 ESUs (Elementary Sampling Unit) of 30m×30m size were established based on variability in composition and age of plantation stands. In-situ LAI was recorded using plant canopy imager during the leaf growing, peak and senescence seasons. The PROSAIL model was calibrated with site-specific biophysical and biochemical parameters before used to the predicted LAI. The plantation LAI was also predicted by an empirical approach using optimally chosen Sentinel-2 vegetation indices. In addition, Sentinel-2 and MODIS LAI products were evaluated with respect to LAI measurements. MLRA-GPR offered best results for predicting LAI of leaf growing (R2 = 0.9, RMSE = 0.14), peak (R2 = 0.87, RMSE = 0.21) and senescence (R2 = 0.86, RMSE = 0.31) seasons while LUT inverted model outperformed VI's based parametric regression model. Vegetation indices (VIs) derived from 740 nm, 783 nm and 2190 nm band combinations of Sentinel-2 offered the best prediction of LAI.

Detection of oil pollution impacts on vegetation using multifrequency SAR, multispectral images with fuzzy forest and random forest methods

Oil pollution harms terrestrial ecosystems. There is an urgent requirement to improve on existing methods for detecting, mapping and establishing the precise extent of oil-impacted and oil-free vegetation. This is needed to quantify existing spill extents, formulate effective remediation strategies and to enable effective pipeline monitoring strategies to identify leakages at an early stage. An effective oil spill detection algorithm based on optical image spectral responses can benefit immensely from the inclusion of multi-frequency Synthetic Aperture Radar (SAR) data, especially when the effect of multi-collinearity is sufficiently reduced. This study compared the Fuzzy Forest (FF) and Random Forest (RF) methods in detecting and mapping oil-impacted vegetation from a post spill multispectral optical sentinel 2 image and multifrequency C and X Band Sentinel - 1, COSMO Skymed and TanDEM-X SAR images. FF and RF classifiers were employed to discriminate oil-spill impacted and oil-free vegetation in a study area in Nigeria. Fuzzy Forest uses specific functions for the selection and use of uncorrelated variables in the classification process to yield an improved result. This method proved an efficient variable selection technique addressing the effects of high dimensionality and multi-collinearity, as the optimization and use of different SAR and optical image variables generated more accurate results than the RF algorithm in densely vegetated areas. An Overall Accuracy (OA) of 75% was obtained for the dense (Tree Cover Area) vegetation, while cropland and grassland areas had 59.4% and 65% OA respectively. However, RF performed better in Cropland areas with OA = 75% when SAR-optical image variables were used for classification, while both methods performed equally well in Grassland areas with OA = 65%. Similarly, significant backscatter differences (P < 0.005) were observed in the C-Band backscatter sample mean of polluted and oil-free TCA, while strong linear associations existed between LAI and backscatter in grassland and TCA. This study demonstrates that SAR based monitoring of petroleum hydrocarbon impacts on vegetation is feasible and has high potential for establishing oil-impacted areas and oil pipeline monitoring.

Estimating persistent oil contamination in tropical region using vegetation indices and random forest regression

The persistence of soil contamination after cessation of oil activities remains a major environmental issue in tropical regions. The assessment of the contamination is particularly difficult on vegetated sites, but promising advances in reflectance spectroscopy have recently emerged for this purpose. This study aimed to exploit vegetation reflectance for estimating low concentrations of Total Petroleum Hydrocarbons (TPH) in soils. A greenhouse experiment was carried out for 42 days on Cenchrus alopecuroides (L.) under realistic tropical conditions. The species was grown on oil-contaminated mud pit soils from industrial sites, with various concentrations of TPH. After 42 days, a significant decrease in plant growth and leaf chlorophyll and carotenoid contents was observed for plants exposed to 5-19 g kg^-1 TPH in comparison to the controls (p < 0.05). Conversely, pigment contents were higher for plants exposed to 1 g kg^-1 TPH (hormesis phenomenon). These modifications proportionally affected the reflectance of C. alopecuroides at leaf and plant scales, especially in the visible region around 550 and 700 nm. 33 vegetation indices were used for linking the biochemical and spectral responses of the species to oil using elastic net regressions. The established models indicated that chlorophylls a and b and β-carotene were the main pigments involved in the modifications of reflectance (R² > 0.7). The same indices also succeeded in estimating the concentrations of TPH using random forest regression, at leaf and plant scales (RMSE = 1.46 and 1.63 g kg^-1 and RPD = 5.09 and 4.44, respectively). Four out of the 33 indices contributed the most to the models (>75%). This study opens up encouraging perspectives for monitoring the cessation of oil activities in tropical regions. Further researches will focus on the application of our approach at larger scale, on airborne and satellite imagery.

Investigating the response of soil and vegetable crops to poultry and cow manure using ground and satellite data

Based on the massive production of cow and poultry manures, farmers in Saudi Arabia are moving towards the application of organic fertilizers in their farms. Therefore, the present work was conducted to study the response of soil and selected vegetable crops to poultry and cow manures, using ground data and Landsat-8 and Hyperion images. The studied vegetable crops are cabbage, cauliflower, broccoli, and lettuce. A total of 100 t ha⁻¹ organic manures were applied as a pre-planting treatment. A 12.5 ha field in Tawdeehiya Farms, 200 km southeast of Riyadh, was earmarked for this study. The field was divided into sectors cultivated with the above-mentioned vegetable crops. Soil characteristics, including the soil pH, the electric conductivity (EC), the nitrogen (N), the phosphorus (P) and the potassium (K), were examined before the application of manures and 25 days after the transplanting process. Observations on crops chlorophyll content, number of leaves, the diameter of merchantable products and yield were also investigated. Furthermore, the relationship between the crop performance and yield was investigated through the satellite images generated vegetation indices (VIs). This study revealed the better performance of poultry manure compared to cow manure in terms of development and production parameters of the experimental crops. Dynamics of the chlorophyll content across the crop growth period revealed that all the tested crops responded significantly (R² = 0.69; P = 0.001) to the poultry manure treatments. Among the tested crops, the chlorophyll content, curd or head sizes and crop yields were quite better in poultry manure applied plots. The investigation of crop yield was significant with poultry manure (R² = 0.64; P = 0.001) than cow manure (R² = 0.57; P = 0.001) using the OSAVI and mNDVI, respectively.

Spatial and temporal variation of the vegetation of the semiarid Puna in a pastoral system in the Pozuelos Biosphere Reserve

This study aimed to analyze the spatial and temporal variation of the vegetation in the northern Argentine Puna, utilizing both field sampling and remote-sensing tools. The study was performed within the Pozuelos Biosphere Reserve (Jujuy province, Argentina), which aims to generate socio-economic development compatible with biodiversity conservation. Our study was designed to analyze the dynamics of the Puna vegetation at local scale and assess and monitor the seasonal (dry and wet seasons), interannual, and spatial variation of the vegetation cover, biomass, dominant species, and vegetation indices. Ten vegetation units (with differences in composition, cover, and high and low stratum biomass) were identified at our study site. The diversity of these vegetation units correlated with geomorphology and soil type. In the dry season, the vegetation unit with greatest vegetation cover and biomass was the Festuca chrysophylla grassland, whereas in the wet season, the units with greatest cover and biomass were vegas (peatlands) and short grasslands. The Festuca chrysophylla grasslands and short grasslands were located in areas with clay soils, except peatlands, associated with valleys and coarse-texture soils. The vegetation indices used (NDVI, SAVI, and MSAVI2) were able to differentiate functional types of vegetation and showed a good statistical fit with cover values. Our results suggest that the integrated utilization of remote-sensing tools and field surveys improves the assessment of the Puna vegetation and would allow a periodic monitoring at production unit scale taking into account its spatial and temporal variation.

Evaluation of long-term estuarine vegetation changes through Landsat imagery

Salt marshes support estuarine biodiversity and provide ecosystem services; however, their general decay is being observed worldwide, in large part due to land reclamation. Accordingly, there is a growing concern about salt marsh preservation status having in mind the promotion of effective management decisions towards their conservation and restoration. Satellite imagery offers the opportunity to monitor land surface dynamics, constituting a fundamental information source for wetland monitoring. This study analyses spatial and temporal vegetation changes within Ria de Aveiro coastal lagoon between 1984 and 2017, by processing and analyzing TM and ETM+ Landsat imagery. A database consisting of 264 cloud-free images was collected and analyzed. The Normalized Difference Water Index was computed using the remote surface reflectance and was then used to distinguish land from water and to estimate the flooded lagoon area. Moreover, the tidal state was determined for each image from a tidal elevation record monitored at the lagoon entrance. Subsequently, four vegetation indices (VI) were computed and their spatial variability in the lagoon area uncovered by water was assessed. Spatially averaged spectral indices were also statistically analyzed and seasonal variations and interannual trends evaluated. Results show that the intertidal area increased, and VI values decreased indicating a possible reduction in the Chlorophyll content and suggesting that the new intertidal regions are mostly covered by mud. The spatially averaged VI values show seasonal patterns, with peaks in spring and summer, coinciding with high biomass productivity periods. The largest flooded area and VI modifications occurred after 1999, suggesting that changes are associated with dredging activities performed in the main lagoon channels. This study reinforced the potential of Landsat archives to monitor coastal wetlands, highlighting their importance for coastal managers of threatened systems, and therefore helping to define management strategies about the ecological conservation of estuarine systems.

High-throughput analysis of leaf physiological and chemical traits with VIS-NIR-SWIR spectroscopy: a case study with a maize diversity panel

BACKGROUND

Hyperspectral reflectance data in the visible, near infrared and shortwave infrared range (VIS-NIR-SWIR, 400-2500 nm) are commonly used to nondestructively measure plant leaf properties. We investigated the usefulness of VIS-NIR-SWIR as a high-throughput tool to measure six leaf properties of maize plants including chlorophyll content (CHL), leaf water content (LWC), specific leaf area (SLA), nitrogen (N), phosphorus (P), and potassium (K). This assessment was performed using the lines of the maize diversity panel. Data were collected from plants grown in greenhouse condition, as well as in the field under two nitrogen application regimes. Leaf-level hyperspectral data were collected with a VIS-NIR-SWIR spectroradiometer at tasseling. Two multivariate modeling approaches, partial least squares regression (PLSR) and support vector regression (SVR), were employed to estimate the leaf properties from hyperspectral data. Several common vegetation indices (VIs: GNDVI, RENDVI, and NDWI), which were calculated from hyperspectral data, were also assessed to estimate these leaf properties.

RESULTS

Some VIs were able to estimate CHL and N (R² > 0.68), but failed to estimate the other four leaf properties. Models developed with PLSR and SVR exhibited comparable performance to each other, and provided improved accuracy relative to VI models. CHL were estimated most successfully, with R² (coefficient of determination) > 0.94 and ratio of performance to deviation (RPD) > 4.0. N was also predicted satisfactorily (R² > 0.85 and RPD > 2.6). LWC, SLA and K were predicted moderately well, with R² ranging from 0.54 to 0.70 and RPD from 1.5 to 1.8. The lowest prediction accuracy was for P, with R² < 0.5 and RPD < 1.4.

CONCLUSION

This study showed that VIS-NIR-SWIR reflectance spectroscopy is a promising tool for low-cost, nondestructive, and high-throughput analysis of a number of leaf physiological and biochemical properties. Full-spectrum based modeling approaches (PLSR and SVR) led to more accurate prediction models compared to VI-based methods. We called for the construction of a leaf VIS-NIR-SWIR spectral library that would greatly benefit the plant phenotyping community for the research of plant leaf traits.

Specalyzer-an interactive online tool to analyze spectral reflectance measurements

Low-cost phenotyping using proximal sensors is increasingly becoming popular in plant breeding. As these techniques generate a large amount of data, analysis pipelines that do not require expertise in computer programming can benefit a broader user base. In this work, a new online tool Specalyzer is presented that allows interactive analysis of the spectral reflectance data generated by proximal spectroradiometers. Specalyzer can be operated from any web browser allowing data uploading, analysis, interactive plots and exporting by point and click using a simple graphical user interface. Specalyzer is evaluated with case study data from a winter wheat fertilizer trial with two fertilizer treatments. Specalyzer can be accessed online at http://www.specalyzer.org.

Combination of lumped hydrological and remote-sensing models to evaluate water resources in a semi-arid high altitude ungauged watershed of Sierra Nevada (Southern Spain)

Assessing water resources in high mountain semi-arid zones is essential to be able to manage and plan the use of these resources downstream where they are used. However, it is not easy to manage an unknown resource, a situation that is common in the vast majority of high mountain hydrological basins. In the present work, the discharge flow in an ungauged basin is estimated using the hydrological parameters of an HBV (Hydrologiska Byråns Vattenbalansavdelning) model calibrated in a "neighboring gauged basin". The results of the hydrological simulation obtained in terms of average annual discharge are validated using the VI-ETo model. This model relates a simple hydrological balance to the discharge of the basin with the evaporation of the vegetal cover of the soil, and this to the SAVI index, which is obtained remotely by means of satellite images. The results of the modeling for both basins underscore the role of the underground discharge in the total discharge of the hydrological system. This is the result of the deglaciation process suffered by the high mountain areas of the Mediterranean arc. This process increases the infiltration capacity of the terrain, the recharge and therefore the discharge of the aquifers that make up the glacial and periglacial sediments that remain exposed on the surface as witnesses of what was the last glaciation.

Estimating and mapping forest biomass using regression models and Spot-6 images (case study: Hyrcanian forests of north of Iran)

Hyrcanian forests of North of Iran are of great importance in terms of various economic and environmental aspects. In this study, Spot-6 satellite images and regression models were applied to estimate above-ground biomass in these forests. This research was carried out in six compartments in three climatic (semi-arid to humid) types and two altitude classes. In the first step, ground sampling methods at the compartment level were used to estimate aboveground biomass (Mg/ha). Then, by reviewing the results of other studies, the most appropriate vegetation indices were selected. In this study, three indices of NDVI, RVI, and TVI were calculated. We investigated the relationship between the vegetation indices and aboveground biomass measured at sample-plot level. Based on the results, the relationship between aboveground biomass values and vegetation indices was a linear regression with the highest level of significance for NDVI in all compartments. Since at the compartment level the correlation coefficient between NDVI and aboveground biomass was the highest, NDVI was used for mapping aboveground biomass. According to the results of this study, biomass values were highly different in various climatic and altitudinal classes with the highest biomass value observed in humid climate and high-altitude class.

Retrieval of canopy water content of different crop types with two new hyperspectral indices: Water Absorption Area Index and Depth Water Index

Crop canopy water content (CWC) is an essential indicator of the crop's physiological state. While a diverse range of vegetation indices have earlier been developed for the remote estimation of CWC, most of them are defined for specific crop types and areas, making them less universally applicable. We propose two new water content indices applicable to a wide variety of crop types, allowing to derive CWC maps at a large spatial scale. These indices were developed based on PROSAIL simulations and then optimized with an experimental dataset (SPARC03; Barrax, Spain). This dataset consists of water content and other biophysical variables for five common crop types (lucerne, corn, potato, sugar beet and onion) and corresponding top-of-canopy (TOC) reflectance spectra acquired by the hyperspectral HyMap airborne sensor. First, commonly used water content index formulations were analysed and validated for the variety of crops, overall resulting in a R² lower than 0.6. In an attempt to move towards more generically applicable indices, the two new CWC indices exploit the principal water absorption features in the near-infrared by using multiple bands sensitive to water content. We propose the Water Absorption Area Index (WAAI) as the difference between the area under the null water content of TOC reflectance (reference line) simulated with PROSAIL and the area under measured TOC reflectance between 911 and 1271 nm. We also propose the Depth Water Index (DWI), a simplified four-band index based on the spectral depths produced by the water absorption at 970 and 1200 nm and two reference bands. Both the WAAI and DWI outperform established indices in predicting CWC when applied to heterogeneous croplands, with a R² of 0.8 and 0.7, respectively, using an exponential fit. However, these indices did not perform well for species with a low fractional vegetation cover (< 30%). HyMap CWC maps calculated with both indices are shown for the Barrax region. The results confirmed the potential of using generically applicable indices for calculating CWC over a great variety of crops.

Potential for using remote sensing to estimate carbon fluxes across northern peatlands - A review

Peatlands store large amounts of terrestrial carbon and any changes to their carbon balance could cause large changes in the greenhouse gas (GHG) balance of the Earth's atmosphere. There is still much uncertainty about how the GHG dynamics of peatlands are affected by climate and land use change. Current field-based methods of estimating annual carbon exchange between peatlands and the atmosphere include flux chambers and eddy covariance towers. However, remote sensing has several advantages over these traditional approaches in terms of cost, spatial coverage and accessibility to remote locations. In this paper, we outline the basic principles of using remote sensing to estimate ecosystem carbon fluxes and explain the range of satellite data available for such estimations, considering the indices and models developed to make use of the data. Past studies, which have used remote sensing data in comparison with ground-based calculations of carbon fluxes over Northern peatland landscapes, are discussed, as well as the challenges of working with remote sensing on peatlands. Finally, we suggest areas in need of future work on this topic. We conclude that the application of remote sensing to models of carbon fluxes is a viable research method over Northern peatlands but further work is needed to develop more comprehensive carbon cycle models and to improve the long-term reliability of models, particularly on peatland sites undergoing restoration.

Agricultural water policy reforms in China: a representative look at Zhangye City, Gansu Province, China

Water resources are essential for agricultural production in the grain-producing region of China, and water shortage could significantly affect the production and international trade of agricultural products. China is placing effort in new policies to effectively respond to changes in water resources due to changes in land use/land cover as well as climatic variations. This research investigates the changes in land, water, and the awareness of farmer vis-à-vis the implementation of water-saving policies in Zhangye City, an experimental site for pilot programs of water resources management in China. This research indicates that the water saved through water-saving programs and changes in cropping structure (2.2 × 10⁸ m³ a^-1) is perhaps lower than the newly increased water withdrawal through corporate-led land reclamation (3.7 × 10⁸ m³ a^-1). Most critically, the groundwater withdrawal has increased. In addition, our survey suggests that local government is facing a dilemma of water conservation and agricultural development. Therefore, the enforcement of the ban on farmland reclamation and irrigation water quotas in our study area is revealed to be relatively loose. In this vein, the engagement of local stakeholders in water governance is essential for the future sustainable management of water resources.

Automatic and adaptive paddy rice mapping using Landsat images: Case study in Songnen Plain in Northeast China

Spatiotemporal explicit information on paddy rice distribution is essential for ensuring food security and sustainable environmental management. Paddy rice mapping algorithm through the Combined Consideration of Vegetation phenology and Surface water variations (CCVS) has been efficiently applied based on the 8day composites time series datasets. However, the great challenge for phenology-based algorithms introduced by unpromising data availability in middle/high spatial resolution imagery, such as frequent cloud cover and coarse temporal resolution, remained unsolved. This study addressed this challenge through developing an automatic and Adaptive paddy Rice Mapping Method (ARMM) based on the cloud frequency and spectral separability. The proposed ARMM method was tested on the Landsat 8 Operational Land Imager (OLI) image (path/row 118/028) in the Songnen Plain in Northeast China in 2015. First, the whole study region was automatically and adaptively subdivided into undisturbed and disturbed regions through a per-pixel strategy based on Landsat image data availability during key phenological stage. Second, image objects were extracted from approximately cloud-free images in disturbed and undisturbed regions, respectively. Third, phenological metrics and other feature images from individual or multiple images were developed. Finally, a flexible automatic paddy rice mapping strategy was implemented. For undisturbed region, an object-oriented CCVS method was utilized to take the full advantages of phenology-based method. For disturbed region, Random Forest (RF) classifier was exploited using training data from CCVS-derived results in undisturbed region and feature images adaptively selected with full considerations of spectral separability and the spatiotemporal coverage. The ARMM method was verified by 473 reference sites, with an overall accuracy of 95.77% and kappa index of 0.9107. This study provided an efficient strategy to accommodate the challenges of phenology-based approaches through transferring knowledge in parts of a satellite scene with finer time series to targets (other parts) with deficit data availability.

NDVI, scale invariance and the modifiable areal unit problem: An assessment of vegetation in the Adelaide Parklands

This research addresses the question as to whether or not the Normalised Difference Vegetation Index (NDVI) is scale invariant (i.e. constant over spatial aggregation) for pure pixels of urban vegetation. It has been long recognized that there are issues related to the modifiable areal unit problem (MAUP) pertaining to indices such as NDVI and images at varying spatial resolutions. These issues are relevant to using NDVI values in spatial analyses. We compare two different methods of calculation of a mean NDVI: 1) using pixel values of NDVI within feature/object boundaries and 2) first calculating the mean red and mean near-infrared across all feature pixels and then calculating NDVI. We explore the nature and magnitude of these differences for images taken from two sensors, a 1.24m resolution WorldView-3 and a 0.1m resolution digital aerial image. We apply these methods over an urban park located in the Adelaide Parklands of South Australia. We demonstrate that the MAUP is not an issue for calculation of NDVI within a sensor for pure urban vegetation pixels. This may prove useful for future rule-based monitoring of the ecosystem functioning of green infrastructure.

Genomic Bayesian functional regression models with interactions for predicting wheat grain yield using hyper-spectral image data

BACKGROUND

Modern agriculture uses hyperspectral cameras that provide hundreds of reflectance data at discrete narrow bands in many environments. These bands often cover the whole visible light spectrum and part of the infrared and ultraviolet light spectra. With the bands, vegetation indices are constructed for predicting agronomically important traits such as grain yield and biomass. However, since vegetation indices only use some wavelengths (referred to as bands), we propose using all bands simultaneously as predictor variables for the primary trait grain yield; results of several multi-environment maize (Aguate et al. in Crop Sci 57(5):1-8, 2017) and wheat (Montesinos-López et al. in Plant Methods 13(4):1-23, 2017) breeding trials indicated that using all bands produced better prediction accuracy than vegetation indices. However, until now, these prediction models have not accounted for the effects of genotype × environment (G × E) and band × environment (B × E) interactions incorporating genomic or pedigree information.

RESULTS

In this study, we propose Bayesian functional regression models that take into account all available bands, genomic or pedigree information, the main effects of lines and environments, as well as G × E and B × E interaction effects. The data set used is comprised of 976 wheat lines evaluated for grain yield in three environments (Drought, Irrigated and Reduced Irrigation). The reflectance data were measured in 250 discrete narrow bands ranging from 392 to 851 nm (nm). The proposed Bayesian functional regression models were implemented using two types of basis: B-splines and Fourier. Results of the proposed Bayesian functional regression models, including all the wavelengths for predicting grain yield, were compared with results from conventional models with and without bands.

CONCLUSIONS

We observed that the models with B × E interaction terms were the most accurate models, whereas the functional regression models (with B-splines and Fourier basis) and the conventional models performed similarly in terms of prediction accuracy. However, the functional regression models are more parsimonious and computationally more efficient because the number of beta coefficients to be estimated is 21 (number of basis), rather than estimating the 250 regression coefficients for all bands. In this study adding pedigree or genomic information did not increase prediction accuracy.

Studying bio-thermal effects at and around MSW dumps using Satellite Remote Sensing and GIS

Estimating negative impacts of MSW dumps on its surrounding environment is the key requirement for any remedial measures. This study has been undertaken to map bio-thermal effects of MSW dumping at and around dumping facilities (non-engineered) using satellite imagery for Faisalabad, Pakistan. Thirty images of Landsat 8 have been selected after validation for the accuracy of their observational details from April 2013 to October 2015. Land Surface Temperature (LST), NDVI, SAVI and MSAVI have been derived from these images through Digital Image Processing (DIP) and have been subjected to spatio-temporal analysis in GIS environment. MSW dump has been found with average temperature elevation of 4.3K and 2.78K from nearby agriculture land and urban settlement respectively. Vegetation health has been used as the bio-indicator of MSW effects and is implemented through NDVI, SAVI, MSAVI. Spatial analyses have been used to mark boundary of bio-thermally affected zone around dumped MSW and measure 700m. Seasonal fluctuations of elevated temperatures and boundary of the bio-thermally affected zones have also been discussed. Based on the direct relation found between vegetation vigor and the level of deterioration within the bio-thermally affected region, use of crops with heavy vigor is recommended to study MSW hazard influence using bio-indicators of vegetation health.

Statistical analysis of land surface temperature-vegetation indexes relationship through thermal remote sensing

Vegetation coverage has a significant influence on the land surface temperature (LST) distribution. In the field of urban heat islands (UHIs) based on remote sensing, vegetation indexes are widely used to estimate the LST-vegetation relationship. This paper devises two objectives. The first analyzes the correlation between vegetation parameters/indicators and LST. The subsequent computes the occurrence of vegetation parameter, which defines the distribution of LST (for quantitative analysis of urban heat island) in Kalaburagi (formerly Gulbarga) City. However, estimation work has been done on the valuation of the relationship between different vegetation indexes and LST. In addition to the correlation between LST and the normalized difference vegetation index (NDVI), the normalized difference build-up index (NDBI) is attempted to explore the impacts of the green land to the build-up land on the urban heat island by calculating the evaluation index of sub-urban areas. The results indicated that the effect of urban heat island in Kalaburagi city is mainly located in the sub-urban areas or Rurban area especially in the South-Eastern and North-Western part of the city. The correlation between LST and NDVI, indicates the negative correlation. The NDVI suggests that the green land can weaken the effect on urban heat island, while we perceived the positive correlation between LST and NDBI, which infers that the built-up land can strengthen the effect of urban heat island in our case study. Although satellite data (e.g., Landsat TM thermal bands data) has been applied to test the distribution of urban heat islands, but the method still needs to be refined with in situ measurements of LST in future studies.