Estimating fractional cover of crop,crop residue,and soil in cropland using broadband remote sensing data and machine learning

The fractional vegetation cover (FVC), crop residue cover (CRC), and bare soil (BS) are three important parameters in vegetation–soil ecosystems, and their correct and timely estimation can improve crop monitoring and environmental monitoring. The triangular space method uses one CRC index and one vegetation index to create a triangular space in which the three vertices represent pure vegetation, crop residue, and bare soil. Subsequently, the CRC, FVC, and BS of mixed remote sensing pixels can be distinguished by their spatial locations in the triangular space. However, soil moisture and crop-residue moisture (SM-CRM) significantly reduce the performance of broadband remote sensing CRC indices and can thus decrease the accuracy of the remote estimation and mapping of CRC, FVC, and BS. This study evaluated the use of broadband remote sensing, the triangular space method, and the random forest (RF) technique to estimate and map the FVC, CRC, and BS of cropland in which SM-CRM changes dramatically. A spectral dataset was obtained using: (1) from a field-based experiment with a field spectrometer; and (2) from a laboratory-based simulation that included four distinct soil types, three types of crop residue (winter-wheat, maize, and rice), one crop (winter wheat), and varying SM-CRM. We trained an RF model [designated the broadband crop-residue index from random forest (CRRF)] that can magnify spectral features of crop residue and soil by using the broadband remote sensing angle indices as input, and uses a moisture-resistant hyperspectral index as the target. The effects of moisture on crop residue and soil were minimized by using the broadband CRRF. Then, the CRRF-NDVI triangular space method was used to estimate and map CRC, FVC, and BS. Our method was validated by using both laboratory- and field-based experiments and Sentinel-2 broadband remote-sensing images. Our results indicate that the CRRF-NDVI triangular space method can reduce the effect of moisture on the broadband remote-sensing of CRC, and may also help to obtain laboratory and field CRC, FVC, and BS. Thus, the proposed method has great potential for application to croplands in which the SM-CRM content changes dramatically.     

基于SPOT 5图像的岩溶地貌单元自动提取方法

通过对峰林、峰丛和岩溶洼地3者的地理特征和影像特征的研究,基于遥感图像本底值提出了能有效反映目标特征的遥感指数——植被指数、土壤亮度指数、图像主成分变换第1主成分值及地形数据等,并构建了遥感指数的集成计算法,建立了遥感自动提取模型.指数集成运算法能够有效地增大峰丛、峰林与其他地物之间的光谱差异,使这些岩溶地貌单元的灰度值高于其他地物,从而利于岩溶地貌单元提取阈值的自动选取.基于构建的遥感自动提取模型先提取了峰丛、峰林信息,并在此基础上提取了岩溶洼地信息.经实验研究表明,该方法具有较高的提取精度和效率.     

A shadow- eliminated vegetation index (SEVI) for removal of self and cast shadow effects on vegetation in rugged terrains

ABSTRACT

The effect of terrain shadow, including the self and cast shadows, is one of the main obstacles for accurate retrieval of vegetation parameters by remote sensing in rugged terrains. A shadow- eliminated vegetation index (SEVI) was developed, which was computed from only red and near-infrared top-of-atmosphere reflectance without other heterogeneous data and topographic correction. After introduction of the conceptual model and feature analysis of conventional wavebands, the SEVI was constructed by ratio vegetation index (RVI), shadow vegetation index (SVI) and adjustment factor (f (Δ)). Then three methods were used to validate the SEVI accuracy in elimination of terrain shadow effects, including relative error analysis, correlation analysis between the cosine of solar incidence angle (cosi) and vegetation indices, and comparison analysis between SEVI and conventional vegetation indices with topographic correction. The validation results based on 532 samples showed that the SEVI relative errors for self and cast shadows were 4.32% and 1.51% respectively. The coefficient of determination between cosi and SEVI was only 0.032 and the coefficient of variation (std/mean) for SEVI was 12.59%. The results indicate that the proposed SEVI effectively eliminated the effect of terrain shadows and achieved similar or better results than conventional vegetation indices with topographic correction.     

Retrieval of EVI from Oceansat 2 Data and Comparison with MODIS Derived EVI

The vegetation index is derived using many remote sensing sensors. Vegetation Index is extensively used and remote sensing has become the primary data source. Number of vegetation indices (VIs) have been developed during the past decades in order to assess the state of vegetation qualitatively and quantitatively. Analysis of vegetation indices has been carried out by many investigators scaling from regional level to global level using the remote sensing data of varying spatial, temporal and radiometric resolutions. There are as many as 14 VIs in use. Globally operational algorithms for generation of NDVI have utilized digital counts, at sensor radiances, ‘normalized’ reflectance (top of the atmosphere), and more recently, partially atmospheric corrected (ozone absorption and molecular scattering) reflectance. Presently NDVI and EVI are standard MODIS data products which are widely used by the scientific community for environmental studies. The OCM sensor in Oceansat 2 is designed for ocean colour studies. The OCM sensor has been used for studying ocean phytoplankton, suspended sediments and aerosol optical depth by many investigators. In addition to its capability of studying the ocean surface, OCM sensor has also the potential to study the land surface features. In a past EVI has been retrieved using OCM sensor of Oceansat 1. However, there is slight change in the band width of Oceansat 2—OCM sensor compared with OCM of Oceansat 1 sensor. In the present paper an attempt has been made to derive EVI using Oceansat 2 OCM sensor and the results have been compared with MODIS data. The enhanced vegetation index (EVI) is calculated using the reflectance values obtained after removing molecular scattering and ozone absorption component from the total radiance detected by the sensor. The band-2, Band-3, band-6 and band-8 corresponding to Blue, Red and Infrared part of the visible spectrum have been used to determine EVI. The result shows that Oceansat 2 derived EVI and MODIS derived EVI are well correlated.     

Integrated approach of using remote sensing and GIS to study watershed prioritization and productivity

Soil data obtained from soil resource inventory, land and climate were derived from the remote sensing satellite data (Landsat TM, bands 1 to 7) and were integrated in GIS environment to obtain the soil erosion loss using USLE model for the watershed area. The priorities of different sub-watershed areas for soil conservation measures were identified. Land productivity index was also used as a measure for land evaluation. Different soil and land attribute maps were generated in GIS, and R,K,LS,C and P factor maps were derived. By integrating these soil erosion map was generated. The mapping units, found not suitable for agriculture production, were delineated and mapped as non-arable land. The area suitable for agricultural production was carved out for imparting the productivity analysis; the land suitable for raising agricultural crops was delineated into different mapping units as productivity ratings good, fair, moderate and poor. The analysis performed using remote sensing and GIS helped to generate the attribute maps with more accuracy and the ability of integrating these in GIS environment provided the ease to get the required kind of analysis. Conventional methods of land evaluation procedures in terms of either soil erosion or productivity are found not comparable with the out put generated by using remote sensing and GIS as the limitations in generating the attribute maps and their integration. The results obtained in this case study show the use of different kinds of data derived from different sources in land evaluation appraisals.     

基于多光谱影像和DEM的泥石流堆积扇识别研究——以白龙江流域武都段为例

选取中国泥石流多发区白龙江流域武都段作为研究区,在对该区域泥石流堆积扇的形态特征和堆积范围进行实地调绘的基础上,利用高分辨率影像(SPOT)进行目视解译,获得研究区部分泥石流堆积扇和非泥石流堆积区的分布范围,将其作为已知样本区。利用该区域多光谱遥感影像(ASTER)和数字高程模型(DEM),提取包含波段比和主分量的几十种特征指标。通过运用方差分析和聚类分析等方法对各指标进行分析计算,选取对区别泥石流堆积扇最具显著意义的指标进行输入,进而采用基于像元的分类方法识别泥石流堆积扇。得到如下结论:SPOT与ASTER融合影像的波段比、主分量指标可以有效地突出土壤岩石中的矿物成分,对泥石流堆积扇的识别具有显著意义;利用筛选出的遥感指标和地形指标作为输入,进行监督分类识别泥石流堆积扇,能够有效地将遥感指标和地形指标相结合,提取的堆积扇覆盖范围与实际情况较为接近。     

Model selection in Bayesian framework to identify the best WorldView-2 based vegetation index in predicting green biomass of salt marshes in the northern Gulf of Mexico

Coastal wetlands are among the most productive ecosystems globally but have experienced dramatic degradation and loss within the past several decades. Vegetation biomass of coastal wetlands is not only the key component of blue carbon storage but also plays an important role in vertical accretion, important for maintaining these habitats under relative sea-level rise. Remote sensing offers a cost-effective approach to study vegetation biomass at a broad spatial scale. We developed statistical models to predict peak aboveground green biomass of Spartina alterniflora and Juncus roemerianus, two dominant species of salt marshes using WorldView-2 satellite imagery at the Grand Bay National Estuarine Research Reserve (NERR) on the Mississippi coast in the northern Gulf of Mexico. The model accounted for nested data structures in the sampled biomass, assimilated uncertainties from data, parameters and model structures, and helped determine the best vegetation index among a variety of commonly-used indices to predict aboveground green biomass. We developed a series of mixed-effects models, which included different combinations of fixed effect(s), random intercept, and random slope(s). The fixed effects were species and one of the 60 vegetation indices derived from a WorldView-2 image obtained on 6 October 2012. The random effect used was site. We implemented the models in a Bayesian framework and selected the best model structure and vegetation index based on minimum posterior predictive loss and deviance information criterion. The results showed that the best vegetation index to predict peak green biomass was the green chlorophyll index derived from the reflectance values of band 8 (near-infrared) and band 3 (green), and its effect on biomass prediction varied among sites. The inclusion of species as a fixed effect improved the model prediction. The study demonstrated the need to account for spatial dependence of data in developing a robust model, and the importance of the second WorldView-2 near-infrared band (860–1040 nm) in predicting aboveground green biomass for the Grand Bay NERR. The analysis using mixed-effects modeling in Bayesian inference which coherently combined field and WorldView-2 data with uncertainties accounted for provides a robust and nondestructive tool for resource managers to monitor the status of coastal wetlands at a high spatial resolution in a timely manner. Through this study, we hope to emphasize the importance of appropriately accounting for nested data structures using mixed-effects models and promote wider application of Bayesian inference to facilitate assimilation of uncertainties in remote sensing applications.     

旱情遥感监测研究进展与应用案例分析

在大范围、长时序的旱情监测中,遥感技术以其快速、经济和大空间范围获取的特点,弥补了基于台站气象数据旱情监测的不足,为防旱和抗旱决策提供了实时、动态、宏观的辅助决策数据。本文对已有旱情遥感监测方法进行分析和整理,将其总结为基于土壤热惯量、基于土壤波谱特征、基于蒸散模型和基于植被指数的旱情监测方法,并对各类方法从监测原理、适用范围和应用进展等方面进行了阐述。在此基础之上,详细介绍一种结合了全球植被水分指数和短波角度归一化指数的优势建立的旱情遥感监测模型和方法。以2010年春季西南地区旱情为应用案例,从监测模型方法、数据处理流程和应用分析等方面,介绍一种基于植被水分指数的旱情监测方法,并对其监测结果进行统计分析与评价。     

遥感与GIS支持下的土壤侵蚀强度快速评价方法研究

 以TM影像、1︰1万数字地形图以及其它辅助数据为基础，以土地利用类型、植被覆盖度以及坡度等作为影响因子，在遥感 和GIS技术的支持下，对余江县洪湖乡的土壤侵蚀强度进行了快速分级评价实验。结果表明，该方法所获取的土壤侵蚀强度信息与 实际情况比较吻合。     

光学与微波植被指数协同反演农作物叶面积指数的可行性分析

光学遥感是目前反演植被叶面积指数LAI（Leaf Area Index）的主要手段,但是当叶面积指数较大时存在光学遥感信息饱和、反演精度显著降低的问题。叶面积指数和平均叶倾角对光学、微波波段范围内反射和散射特性都有重要影响,主要表现在植被结构参数的变化可以引起冠层孔隙率和消光截面大小的改变。本文以典型农作物玉米为例,通过构建统一的PROSAIL和MIMICS模型输入参数,生成一套玉米全生长期光学二向反射率和全极化微波后向散射系数模拟库和冠层参数库。通过对模拟数据与LAI敏感性和相关性分析得出：（1）光学植被指数MNDVI_{(800 nm,2000 nm)},在LAI为0—3时敏感,基于MNDVI与LAI的回归模型可以估算LAI变化 0.4的情况,RMSE是0.33,R²是0.958。（2）微波植被指数SAR_{SRVI(1.4 GHz HH,9.6 GHz HV)},在LAI为3—6时敏感,基于SAR_SRVI与LAI的回归模型可以估算LAI变化1的情况,RMSE为0.22,R²是0.9839。研究表明,采用分段敏感的植被指数,协同光学和微波遥感反演玉米全生长期叶面积指数是可行的。     

Developing soil indices based on brightness,darkness, and greenness to improve land surface mapping accuracy

Soil, as one of the three basic biophysical components, has been understudied using remote sensing techniques compared to vegetation and impervious surface areas (ISA). This study characterized land surfaces based on the brightness–darkness–greenness model. These three dimensions, brightness, darkness, and greenness, were represented by the first Tasseled Cap Transformation (TC1), Normalize Difference Snow Index (NDSI), and Normalized Difference Vegetation Index (NDVI), respectively. The Ratio Index for Bright Soil (RIBS) was developed based on TC1 and NDSI, and the Product Index for Dark Soil (PIDS) was established by TC1 and NDVI. Their applications to the Landsat 8 Operational Land Imager images and 500 m 8-day composite Moderate Resolution Imaging Spectroradiometer (MODIS) in China revealed the efficiency. The two soil indices proficiently highlighted soil covers with consistently the smallest values, due to larger TC1 and smaller NDSI values in bright soil, and smaller NDVI and TC1 values in dark soil. The RIBS is capable of distinguishing bright soil from ISA without masking vegetation and water body. The spectral separability bright soil and ISA were perfect, with a Jeffries–Matusita distance of 1.916. And the PIDS was the only soil index that could discriminate dark soil from other land covers including ISA. The soil areas in China were classified using a simple threshold method based on MODIS images. An overall accuracy of 94.00% was obtained, with the kappa index of 0.8789. This study provided valuable insights into developing indices for characterizing land surfaces from different perspectives.     

Comparison of vegetation indices for practicable homology

Vegetation indices are widely used to assess quantitatively the biophysical characteristics of vegetation from remote sensing measurements. Different indices have their own advantages in retrieving vegetation information. It is very difficult to precisely attribute any vegetation index to any particular vegetation biophysical parameter. This study examines the correlations among different vegetation indices derived from a set of mustard, gram and wheat fields at three different phenological growth stages. The results are presented as correlation matrices along with correlation scatter plots. Homologous (equi-magnitude) vegetation information is represented by NDVI, PVI and AtRVI for wheat crop with leaf area index less than 1.     

基于主成分分析的植被指数与叶面积指数相关性研究

综合分析了玉米叶面积指数与几种常见光谱植被指数相关性,确定主成分分析方法在反演叶面积指数中的作用。首先,借助MATLAB编程软件,以植被指数与玉米叶面积指数相关性最高为原则,选出遥感影像上各种植被指数,其波段组合为NDVI(752.4/701.5),RVI(752.4/701.5),MSR(752.4/701.5),SAVI(823.7/701.5),MSAVI(823.7/701.5),然后,对这5种植被指数进行主成分分析,建立LAI-VI多元逐步回归模型,并对模型精度进行验证,总体估测精度为96.237%。经实验验证,利用主成分分析方法在反演植被叶面积指数时能够起到较好的效果,具有广泛的应用前景。     

Angle effects of vegetation indices and the influence on prediction of SPAD values in soybean and maize

To study the anisotropy of vegetation indices (VIs) and explore its influence on the retrieval accuracy of canopy soil-plant analyzer development (SPAD) value, the bidirectional reflectance distribution function (BRDF) models of soybean and maize are calculated from the multi-angle hyperspectral images acquired by UAV, respectively. According to the reflectance extracted from the BRDF model, the dependences of 16 commonly-used VIs on observation angles are analyzed, and the SPAD values of maize and soybean canopy are predicted by using the 16 VI values at different observation angles and their combinations as input parameters. The results show that the 16 VIs have different sensitivity to angle in the principal plane: green ratio vegetation index (GRVI), ratio vegetation index (RVI), red edge chlorophyll index (CIRE), and modified chlorophyll absorption in reflectance index/optimized soil-adjusted vegetation index (MCARI/OSAVI) are very sensitive to angles, among which MCARI/OSAVI of maize fluctuated the most (138.83 %); in contrast, the green optimal soil adjusted vegetation index (GOSAVI), normalized difference vegetation index (NDVI), and green normalized difference vegetation index (GNDVI) hardly change with the observation angles. In terms of SPAD prediction, the accuracy of different VI is different, the mean absolute error (MAE) showed that MCARI1 provided the highest accuracy of retrieval for soybean (MAE=1.617), while for maize it was MCARI/OSAVI (MAE=2.422). However, when using the same VI, there was no significant difference in the accuracy of the predicted results, whether the VI from different angles was used or the combination of multi-angles was used. The present results provide guiding significance and practical value for the retrieval of SPAD value in vegetation canopies and in-depth applications of multi-angular remote sensing.     

利用遥感和GIS研究内蒙古中西部地区环境变化

利用TM和MSS卫星遥感数据提取反映生态环境的植被、土壤亮度、湿度、热度指数，结合气候数据和其它地学辅助信息，在GIS的支持下建立环境质量评价模型；利用该模型评价了内蒙古中西部地区19876、1987、1996年跨越20年的环境变化，从区域平均环境质量指数的变化和各级指数分布的区域面积变化两方面说明了研究区20年来的环境退化；分析了气候因子对环境质量变化的影响，定量说明了半干旱地区影响环境变化的气候因子主要是湿润度，指出20年来人为因素对环境质量的影响呈现越来越大的趋势。     

Monitoring winter wheat growth in North China by combining a crop model and remote sensing data

Both of crop growth simulation models and remote sensing method have a high potential in crop growth monitoring and yield prediction. However, crop models have limitations in regional application and remote sensing in describing the growth process. Therefore, many researchers try to combine those two approaches for estimating the regional crop yields. In this paper, the WOFOST model was adjusted and regionalized for winter wheat in North China and coupled through the LAI to the SAIL–PROSPECT model in order to simulate soil adjusted vegetation index (SAVI). Using the optimization software (FSEOPT), the crop model was then re-initialized by minimizing the differences between simulated and synthesized SAVI from remote sensing data to monitor winter wheat growth at the potential production level. Initial conditions, which strongly impact phenological development and growth, and which are hardly known at the regional scale (such as emergence date or biomass at turn-green stage), were chosen to be re-initialized. It was shown that re-initializing emergence date by using remote sensing data brought simulated anthesis and maturity date closer to measured values than without remote sensing data. Also the re-initialization of regional biomass weight at turn-green stage led that the spatial distribution of simulated weight of storage organ was more consistent to official yields. This approach has some potential to aid in scaling local simulation of crop phenological development and growth to the regional scale but requires further validation.     

Effects of detailed soil spatial information on watershed modeling across different model scales

Hydro-ecological modelers often use spatial variation of soil information derived from conventional soil surveys in simulation of hydro-ecological processes over watersheds at mesoscale (10–100 km²). Conventional soil surveys are not designed to provide the same level of spatial detail as terrain and vegetation inputs derived from digital terrain analysis and remote sensing techniques. Soil property layers derived from conventional soil surveys are often incompatible with detailed terrain and remotely sensed data due to their difference in scales. The objective of this research is to examine the effect of scale incompatibility between soil information and the detailed digital terrain data and remotely sensed information by comparing simulations of watershed processes based on the conventional soil map and those simulations based on detailed soil information across different simulation scales. The detailed soil spatial information was derived using a GIS (geographical information system), expert knowledge, and fuzzy logic based predictive mapping approach (Soil Land Inference Model, SoLIM). The Regional Hydro-Ecological Simulation System (RHESSys) is used to simulate two watershed processes: net photosynthesis and stream flow. The difference between simulation based on the conventional soil map and that based on the detailed predictive soil map at a given simulation scale is perceived to be the effect of scale incompatibility between conventional soil data and the rest of the (more detailed) data layers at that scale. Two modeling approaches were taken in this study: the lumped parameter approach and the distributed parameter approach. The results over two small watersheds indicate that the effect does not necessarily always increase or decrease as the simulation scale becomes finer or coarser. For a given watershed there seems to be a fixed scale at which the effect is consistently low for the simulated processes with both the lumped parameter approach and the distributed parameter approach.     

Crop yield estimation model for Iowa using remote sensing and surface parameters

Numerous efforts have been made to develop various indices using remote sensing data such as normalized difference vegetation index (NDVI), vegetation condition index (VCI) and temperature condition index (TCI) for mapping and monitoring of drought and assessment of vegetation health and productivity. NDVI, soil moisture, surface temperature and rainfall are valuable sources of information for the estimation and prediction of crop conditions. In the present paper, we have considered NDVI, soil moisture, surface temperature and rainfall data of Iowa state, US, for 19 years for crop yield assessment and prediction using piecewise linear regression method with breakpoint. Crop production environment consists of inherent sources of heterogeneity and their non-linear behavior. A non-linear Quasi-Newton multi-variate optimization method is utilized, which reasonably minimizes inconsistency and errors in yield prediction.     

Soil erosion modelled with USLE and PESERA using QuickBird derived vegetation parameters in an alpine catchment

The focus of soil erosion research in the Alps has been in two categories: (i) on-site measurements, which are rather small scale point measurements on selected plots often constrained to irrigation experiments or (ii) off-site quantification of sediment delivery at the outlet of the catchment. Results of both categories pointed towards the importance of an intact vegetation cover to prevent soil loss. With the recent availability of high-resolution satellites such as IKONOS and QuickBird options for detecting and monitoring vegetation parameters in heterogeneous terrain have increased. The aim of this study is to evaluate the usefulness of QuickBird derived vegetation parameters in soil erosion models for alpine sites by comparison to Cesium-137 (Cs-137) derived soil erosion estimates. The study site (67 km²) is located in the Central Swiss Alps (Urseren Valley) and is characterised by scarce forest cover and strong anthropogenic influences due to grassland farming for centuries. A fractional vegetation cover (FVC) map for grassland and detailed land-cover maps are available from linear spectral unmixing and supervised classification of QuickBird imagery. The maps were introduced to the Pan-European Soil Erosion Risk Assessment (PESERA) model as well as to the Universal Soil Loss Equation (USLE). Regarding the latter model, the FVC was indirectly incorporated by adapting the C factor. Both models show an increase in absolute soil erosion values when FVC is considered. In contrast to USLE and the Cs-137 soil erosion rates, PESERA estimates are low. For the USLE model also the spatial patterns improved and showed “hotspots” of high erosion of up to 16 t ha⁻¹ a⁻¹. In conclusion field measurements of Cs-137 confirmed the improvement of soil erosion estimates using the satellite-derived vegetation data.     

Risk assessment of soil erosion in semi-arid mountainous watershed in Saudi Arabia by RUSLE model coupled with remote sensing and GIS

Soil erosion is the most important factor in land degradation and influences desertification in semi-arid areas. A comprehensive methodology that integrates revised universal soil loss equation (RUSLE) model and GIS was adopted to determine the soil erosion risk (SER) in semi-arid Aseer region, Saudi Arabia. Geoenvironmental factors viz. rainfall (R), soil erodibility (K), slope (LS), cover management and practice factors were computed to determine their effects on average annual soil loss. The high potential soil erosion, resulting from high denuded slope, devoid of vegetation cover and high intensity rainfall, is located towards the north western part of the study area. The analysis is investigated that the SER over the vegetation cover including dense vegetation, sparse vegetation and bushes increases with the higher altitude and higher slope angle. The erosion maps generated with RUSLE integrated with GIS can serve as effective inputs in deriving strategies for land planning/management in the environmentally sensitive mountainous areas.