首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献，搜索用时 15 毫秒
1.
This paper presents a new approach to estimate spatial Sun-Induced Fluorescence (SIF) using the empirical relationship between simulated Canopy Chlorophyll Concentration (CCC) and simulated SIF. PROSAIL model [PROpriétésSPECTrales (PROSPECT) and Scattering by Arbitrarily Inclined Leaves (SAIL) models] was used to simulate CCC. CCC maps were generated through an Automated Radiative Transfer Model Operator (ARTMO) using the PROSAIL model and Sentinel-2 Multi-Spectral Imager (MSI) imagery. The Soil Canopy Observation, Photochemistry, and Energy fluxes (SCOPE) model was used to simulate SIF emitted at 740 nm (SIF740), at 760 nm (SIF760), and top of canopy (SIFTOC) (640-850 nm). The SCOPE model, configured with the specification of the Sentinel-2 sensor, simulates SIF within the spectrum range of 640-850 nm. A non-linear logarithmic relationship (R2>0.9, p < 0.05) was observed between simulated SIF and simulated CCC. Simulated CCC was linearly related to observed CCC with R2 0.88, 0.92 and 0.89 and RMSE = 0.04, 0.17 and 0.09 gm/m2 at p < 0.05 for summer, post-monsoon and early winter respectively. Whereas, the simulated CCC did not capture the full range of CCC variability for the post-monsoon season. Simulated SIF (SIF760) was well correlated with SIF from Orbiting Carbon Observatory-2 (OCO-2) satellite with R2 0.68, 0.73 and 0.73 (RMSE = <1 W/m2/sr/μm, p < 0.05) for the month of summer (April), pre-monsoon (May) and early winter season (November) respectively. Temporal SIFTOC effectively captured the seasonal variability associated with the phenology of deciduous tree species. Among various Sentinel-2 MSI derived VIs, Red Edge NDVI (RENDVI) exhibited maximum sensitivity with SIF (highest monthly average R2> 0.6, p < 0.05). The spatial SIF would serve as an useful link between airborne /satellite derived SIF and in-situ fluorescence measurements to understand multiscale SIF variability of terrestrial vegetation.  相似文献   

2.
Sentinel-2数据的冬小麦地上干生物量估算及评价   总被引：3，自引：0，他引：3  
郑阳  吴炳方  张淼 《遥感学报》2017,21(2):318-328
作物生物量快速精确的监测对于农业资源的合理利用与农田的精准管理具有重要意义。近年来,遥感技术因其独特的优势已被广泛用于作物生物量的估算中。本文主要针对不同宽波段植被指数在冬小麦生物量(文中的生物量均是指地上干生物量)估算方面的表现进行探索。首先利用欧洲空间局最新的Sentinel-2A卫星数据提取出17种常见的植被指数,之后分别构建其与相应时期内采集的冬小麦地上生物量间的最优估算模型,通过分析两者间的相关性与敏感性,获取适宜进行生物量估算的指数。最后,绘制了研究区的生物量空间分布图。结果表明,所选的植被指数均与生物量显著相关。其中,红边叶绿素指数(CI_(re))与生物量的估算精度最高(决定性系数R~2为0.83;均方根误差RMSE为180.29 g·m~(–2))。虽然相关性较高,但部分指数,如归一化差值植被指数(NDVI)等在生物量较高时会出现饱和现象,从而导致生物量的低估。而加入红边波段的指数不仅能够延缓指数的饱和趋势,而且能够提高反演精度。此外,通过敏感性分析发现,归一化差值指数和比值指数分别在作物生长的早期和中后期对生物量的变化保持较高的敏感性。由于红边比值指数(SR_(re))和MERIS叶绿素敏感指数(MTCI)在冬小麦全生长季内一直对生物量的变化保持高灵敏性,二者是生物量估算中最为稳定的指数。  相似文献   

3.
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 30 m × 30 m 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.  相似文献   

4.
Grass nitrogen (N) and phosphorus (P) concentrations are direct indicators of rangeland quality and provide imperative information for sound management of wildlife and livestock. It is challenging to estimate grass N and P concentrations using remote sensing in the savanna ecosystems. These areas are diverse and heterogeneous in soil and plant moisture, soil nutrients, grazing pressures, and human activities. The objective of the study is to test the performance of non-linear partial least squares regression (PLSR) for predicting grass N and P concentrations through integrating in situ hyperspectral remote sensing and environmental variables (climatic, edaphic and topographic). Data were collected along a land use gradient in the greater Kruger National Park region. The data consisted of: (i) in situ-measured hyperspectral spectra, (ii) environmental variables and measured grass N and P concentrations. The hyperspectral variables included published starch, N and protein spectral absorption features, red edge position, narrow-band indices such as simple ratio (SR) and normalized difference vegetation index (NDVI). The results of the non-linear PLSR were compared to those of conventional linear PLSR. Using non-linear PLSR, integrating in situ hyperspectral and environmental variables yielded the highest grass N and P estimation accuracy (R2 = 0.81, root mean square error (RMSE) = 0.08, and R2 = 0.80, RMSE = 0.03, respectively) as compared to using remote sensing variables only, and conventional PLSR. The study demonstrates the importance of an integrated modeling approach for estimating grass quality which is a crucial effort towards effective management and planning of protected and communal savanna ecosystems.  相似文献   

5.
This study assessed the strength of Sentinel-2 multispectral instrument (MSI) derived Red Edge (RE) bands in estimating Leaf Area Index (LAI) and mapping canopy storage capacity (CSC) for hydrological applications in wattle infested ecosystems. To accomplish this objective, this study compared the estimation strength of models derived, using standard bands (all bands excluding the RE band) with those including RE bands, as well as different vegetation indices. Sparse Partial Least Squares (SPLSR) and Partial Least Squares Regression (PLSR) ensembles were used in this study. Results showed that the RE spectrum covered by the Sentinel-2 MSI satellite reduced the estimation error by a magnitude of 0.125 based on simple ratio (RE SR) vegetation indices from 0.157 m2· m?2 based on standard bands, and by 0.078 m2· m?2 based on red edge normalised difference vegetation (NDVI-RE). The optimal models for estimating LAI to map CSC were obtained based on the RE bands centered at 705 nm (Band 5), 740 nm (Band 6), 783 nm (Band 7) as well as 865 nm (Band 8a). A root mean square error of prediction (RMSEP) of 0.507 m2· m?2 a relative root mean square error of prediction (RRMSEP) of 11.3% and R2 of 0.91 for LAI and a RMSEP of 0.246 m2/m2 (RRMSEP = 7.9%) and R2 of 0.91 for CSC were obtained. Overall, the findings of this study underscore the relevance of the new copernicus satellite product in rapid monitoring of ecosystems that are invaded by alien invasive species.  相似文献   

6.
The objective of this study was to investigate the entire spectra (from visible to the thermal infrared; 0.390–14.0 μm) to retrieve leaf water content in a consistent manner. Narrow-band spectral indices (calculated from all possible two band combinations) and a partial least square regression (PLSR) were used to assess the strength of each spectral region. The coefficient of determination (R2) and root mean square error (RMSE) were used to report the prediction accuracy of spectral indices and PLSR models. In the visible-near infrared and shortwave infrared (VNIR–SWIR), the most accurate spectral index yielded R2 of 0.89 and RMSE of 7.60%, whereas in the mid infrared (MIR) the highest R2 was 0.93 and RMSE of 5.97%. Leaf water content was poorly predicted using two-band indices developed from the thermal infrared (R2 = 0.33). The most accurate PLSR model resulted from MIR reflectance spectra (R2 = 0.96, RMSE = 4.74% and RMSE cross validation RMSECV = 6.17%) followed by VNIR–SWIR reflectance spectra (R2 = 0.91, RMSE = 6.90% and RMSECV = 7.32%). Using thermal infrared (TIR) spectra, the PLSR model yielded a moderate retrieval accuracy (R2 = 0.67, RMSE = 13.27% and RMSECV = 16.39%). This study demonstrated that the mid infrared (MIR) and shortwave infrared (SWIR) domains were the most sensitive spectral region for the retrieval of leaf water content.  相似文献   

7.
Accurate assessment of phytoplankton chlorophyll-a (Chla) concentration in turbid waters by means of remote sensing was challenging due to the optical complexity of turbid waters. Recently, a conceptual model containing reflectance in three spectral bands in the red and near-infrared range of the spectrum was suggested for retrieving Chla concentrations in turbid productive waters. The objective of this paper was to evaluate the performance of this three-band model to estimate Chla concentration in the Pearl River Estuary (PRE), China. Reflectance spectra of surface water and water samples were collected concurrently. The samples contained variable Chla (4.80-92.60 mg/m3) and total suspended solids (0.4-55.2 mg/L dry wt). Colored dissolved organic matter (CDOM) absorption at 400 nm was 0.40-1.41 m−1; turbidity ranged from 4 to 25 NTU (Nephelometric Turbidity Units). The three-band model was spectrally calibrated by iterative and least-square linear regression methods to select the optimal spectral bands for the most accurate Chla estimation. Strong linear relationships (R2=0.81, RMSE=1.4 mg/m3, N=32) were established between measured Chla and the levels obtained from the calibrated three-band model [R−1(684)-R−1(690)]×R(718), where R(λ) was the reflectance at wavelength λ. The calibrated three-band model was independently validated (R2=0.9521, RMSE=6.44 mg/m3, N=16) and applied to retrieve Chla concentrations from the calibrated EO-1 Hyperion reflectance data in the PRE on December 21, 2006. The EO-1 Hyperion-derived Chla concentrations were further validated using synchronous in situ data collected on the same day (R2=0.64, RMSE=2 mg/m3, N=9). The spatial tendency of Chla distribution mapping by Hyperion showed gradually increased concentrations of Chla farther from the river mouths (although decreasing from east to west), which were disturbed by the combination of river outlets and tidal current in Lingding Bay of the PRE. This observation conformed to previous observations and studies, and could reasonably be explained by geographical changes. Also, results indicated that the slope of the three-band regression line decreased as the Chla concentration increased, resulting in the first sensitive band of the three-band model to move towards short wavelengths. These findings validated the rationale behind the conceptual model and demonstrated the robustness of this algorithm for Chla retrieval from in situ data and the Hyperion satellite sensor in turbid estuarine waters of the PRE, China.  相似文献   

8.
Persian oak (Quercus Brantii Lindl.) which is the most widely distributed tree in the Zagros Mountain forests is affected by western dust storms, mostly originating in Iraq, and harsh water stress as well. The objective of this research is to analyze the spectral behavior of Persian oak under water and dust stress scenarios, aiming to pave the way for modeling the stresses of drought and dust storms on oak trees using remote sensing images. Experiments were carried out on 54 two-year old oak tree seedlings, using a portable wind tunnel in greenhouse conditions. Water stress was induced on seedlings by means of changes in irrigation practices, i.e. well-watered (100 % field capacity), medium water deficit condition (40 % field capacity), and severe water deficit condition (20 % field capacity) treatments. Dust stress is also investigated by using three different dust particle concentrations, i.e. 350, 750 and 1500 (μg/m³). The spectrometry experiments were carried out at leaf and canopy levels in dark room by Fieldspec-3-ASD spectrometer. Spectral analysis was conducted using four procedures: (i) narrow-band spectral indices analysis, (ii) geometric indicators extraction from absorption features, (iii) Partial Least Squares Regression (PLSR), and SVM classifier. Results show that water stress could be modeled much better using PLSR statistic (R2 = 0.87, RMSE = 0.12), narrow-band indices analysis (R2cv = 0.75, RMSEcv = 0.17), and continuum removal (R2 = 0.71, RMSE = 0.20), respectively. For dust stress, PLSR (R2 = 0.83, RMSE = 0.14) and narrow-band indices (R2 cv = 0.7, RMSE cv = 0.30) showed the best results, respectively. SVM could successfully separate stressed and not-stressed samples and also the stress types at both leaf and canopy levels, but it could not distinguish the different levels of stresses.  相似文献   

9.
In this study we combined selected vegetation indices (VIs) and plant height information to estimate biomass in a summer barley experiment. The VIs were calculated from ground-based hyperspectral data and unmanned aerial vehicle (UAV)-based red green blue (RGB) imaging. In addition, the plant height information was obtained from UAV-based multi-temporal crop surface models (CSMs). The test site is a summer barley experiment comprising 18 cultivars and two nitrogen treatments located in Western Germany. We calculated five VIs from hyperspectral data. The normalised ratio index (NRI)-based index GnyLi (Gnyp et al., 2014) showed the highest correlation (R2 = 0.83) with dry biomass. In addition, we calculated three visible band VIs: the green red vegetation index (GRVI), the modified GRVI (MGRVI) and the red green blue VI (RGBVI), where the MGRVI and the RGBVI are newly developed VI. We found that the visible band VIs have potential for biomass prediction prior to heading stage. A robust estimate for biomass was obtained from the plant height models (R2 = 0.80–0.82). In a cross validation test, we compared plant height, selected VIs and their combination with plant height information. Combining VIs and plant height information by using multiple linear regression or multiple non-linear regression models performed better than the VIs alone. The visible band GRVI and the newly developed RGBVI are promising but need further investigation. However, the relationship between plant height and biomass produced the most robust results. In summary, the results indicate that plant height is competitive with VIs for biomass estimation in summer barley. Moreover, visible band VIs might be a useful addition to biomass estimation. The main limitation is that the visible band VIs work for early growing stages only.  相似文献   

10.
Assessment of vegetation water content is critical for monitoring vegetation condition, detecting plant water stress, assessing the risk of forest fires and evaluating water status for irrigation. The main objective of this study was to investigate the performance of various mono- and multi-variate statistical methods for estimating vegetation water content (VWC) from hyper-spectral data. Hyper-spectral data is influenced by multi-collinearity because of a large number of (independent) spectral bands being modeled by a small number of (dependent) biophysical variables. Therefore, some full spectrum methods that are known to be suitable for analyzing multi-collinear data set were chosen. Canopy spectral reflectance was obtained with a GER 3700 spectro-radiometer (400–2400 nm) in a laboratory setting and VWC was measured by calculating wet/dry weight difference per unit of ground area (g/m2) of each plant canopy (n = 95). Three multivariate statistical methods were applied to estimate VWC: (1) partial least square regression, (2) artificial neural network and (3) principal component regression. They were selected to minimize the problem related to multi-collinearity. For comparison, uni-variate techniques including narrow band ratio water index (RWI), normalized difference water index (NDWI), second soil adjusted vegetation index (SAVI2) and transferred soil adjusted vegetation index (TSAVI) were applied. For each type of vegetation index, all two-band combinations were evaluated to determine the best band combination. Validation of the methods was based on the cross validation procedure and using three statistical indicators: R2, RMSE and relative RMSE. The cross-validated results identified PLSR as the regression model providing the most accurate estimates of VWC among the various methods. The result revealed that this model is highly recommended for use with multi-collinear datasets (RCV2=0.94, RRMSECV = 0.23). Principal component regression exhibited the lowest accuracy among the multivariate models (RCV2=0.78, RRMSECV = 0.41).  相似文献   

11.
Developing models for estimating aboveground biomass (AGB) in naturally growing forests is critical for climate change modelling. AGB models developed using satellite imagery varies with study area, depending on the complexity of vegetation and landscape structure, which affects the upwelling radiance. We assessed the potential of SPOT-6 imagery in predicting AGB of trees planted at different time periods, using image texture combinations. Image texture variables were computed from the SPOT6 pan-sharpened image data, which is characterised by a 1.5 m spatial resolution. In addition, we incorporated the minimal variance technique to select the optimum window sizes that best captures AGB variation in our study area. The results showed that image texture was able to detect AGB for both mature and young trees, however, models detecting mature trees were more superior, with accuracies of R2 = 0.70 and 0.25 for 2009–2011 and 2011–2013 plantation phases, respectively. In addition, our results showed that the three band texture ratios yielded the highest accuracy (R2 = 0.88 and RMSE = 54.54 kg m−2) compared to two texture (R2 = 0.85 and RMSE = 60.65 kg m−2) and single texture band combinations (R2 = 0.64 and RMSE = 94.13 kg m−2). A frequency analysis was also run to determine which bands appeared more frequently in the selected texture band models. The frequency analysis revealed that both the red and green bands appeared more frequently on the selected texture band variables, indicating that they were more sensitive to the variation of AGB in our study area. The results showed high variation in AGB within the Buffelsdraai reforestation site, especially due to varying tree plantation phases as well as topography. In essence, the study demonstrated the possibility of image texture combinations computed from the SPOT-6 image in estimating AGB.  相似文献   

12.
机载激光雷达及高光谱的森林乔木物种多样性遥感监测   总被引：1，自引：0，他引：1  
利用机载LiDAR和高光谱数据并结合37个地面调查样本数据,基于结构差异与光谱变异理论,通过相关分析法分别筛选了3个最优林冠结构参数和6个最优光谱指数,在单木尺度上利用自适应C均值模糊聚类算法,在神农架国家自然保护区开展森林乔木物种多样性监测,实现了森林乔木物种多样性的区域成图。研究结果表明,(1)基于结合形态学冠层控制的分水岭算法可以获得较高精度的单木分割结果(R~2=0.88,RMSE=13.17,P0.001);(2)基于LiDAR数据提取的9个结构参数中,95%百分位高度、冠层盖度和植被穿透率为最优结构参数,与Shannon-Wiener指数的相关性达到R~2=0.39—0.42(P0.01);(3)基于机载高光谱数据筛选的16个常用的植被指数中,CRI、OSAVI、Narrow band NDVI、SR、Vogelmann index1、PRI与Shannon-Wiener指数的相关性最高(R~2=0.37—0.45,P0.01);(4)在研究区,利用以30 m×30 m为窗口的自适应模糊C均值聚类算法可预测的最大森林乔木物种数为20,物种丰富度的预测精度为R~2=0.69,RMSE=3.11,Shannon-Wiener指数的预测精度为R~2=0.70,RMSE=0.32。该研究在亚热带森林开展乔木物种多样性监测,是在区域尺度上进行物种多样性成图的重要实践,可有效补充森林生物多样性本底数据的调查手段,有助于实现生物多样性的长期动态监测及科学分析森林物种多样性的现状和变化趋势。  相似文献   

13.
ABSTRACT

Several machine learning regression models have been advanced for the estimation of crop biophysical parameters with optical satellite imagery. However, literature on the comparative performances of such models is still limited in range and scope, especially under multiple data sources, despite the potential of multi-source imagery to improving crop monitoring in cloudy areas. To fill in this knowledge gap, this study explored the synergistic use of Landsat-8, Sentinel-2A, China’s environment and disaster monitoring and forecasting satellites (HJ-1 A and B) and Gaofen-1 (GF-1) data to evaluate four machine learning regression models that include Random Forest (RF), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), and Gradient Boosting Decision Tree (GBDT), for rice dry biomass estimation and mapping. Taking a major rice cultivation area in southeast China as case study during the 2016 and 2017 growing seasons, a cross-calibrated time series of the Enhanced Vegetation Index (EVI) was obtained from the quad-source optical imagery and on which the aforementioned models were applied, respectively. Results indicate that in the before rice heading scenario, the most accurate dry biomass estimates were obtained by the GBDT model (R2 of 0.82 and RMSE of 191.8 g/m2) followed by the RF model (R2 of 0.79 and RMSE of 197.8 g/m2). After heading, the k-NN model performed best (R2 of 0.43 and RMSE of 452.1 g/m2) followed by the RF model (R2 of 0.42 and RMSE of 464.7 g/m2). Whist the k-NN model performed least in the before heading scenario, SVM performed least in the after heading scenario. These findings may suggest that machine learning regression models based on an ensemble of decision trees (RF and GBDT) are more suitable for the estimation of rice dry biomass, at least with optical satellite imagery. Studies that would extend the evaluation of these machine learning models, to other parameters like leaf area index, and to microwave imagery, are hereby recommended.  相似文献   

14.
ABSTRACT

Digitizing the land surface temperature (Ts) and surface soil moisture (mv) is essential for developing the intelligent Digital Earth. Here, we developed a two parameter physical-based passive microwave remote sensing model for jointly retrieving Ts and mv using the dual-polarized Tb of Aqua satellite advanced microwave scanning radiometer (AMSR-E) C-band (6.9 GHz) based on the simplified radiative transfer equation. Validation using in situ Ts and mv in southern China showed the average root mean square errors (RMSE) of Ts and mv retrievals reach 2.42 K (R2 = 0.61, n = 351) and 0.025 g cm?3 (R2 = 0.68, n = 663), respectively. The results were also validated using global in situ Ts (n = 2362) and mv (n = 1657) of International Soil Moisture Network. The corresponding RMSE are 3.44 k (R2 = 0.86) and 0.039 g cm?3 (R2 = 0.83), respectively. The monthly variations of model-derived Ts and mv are highly consistent with those of the Moderate Resolution Imaging Spectroradiometer Ts (R2 = 0.57; RMSE = 2.91 k) and ECV_SM mv (R2 = 0.51; RMSE = 0.045 g cm?3), respectively. Overall, this paper indicates an effective way to jointly modeling Ts and mv using passive microwave remote sensing.  相似文献   

15.
This paper examines the use of canopy reflectance for different units of measurements of carotenoids estimation. Field spectral measurements were collected over cotton in different intensive field campaigns organized during the growing seasons of 2010 and 2011. Three units of measurement were evaluated carotenoids expressed as a mass per unit soil surface area (g/m2), a mass per unit leaf area (μg/cm2), and a mass per unit fresh leaf weight (mg/g), respectively. Four methods were compared to retrieve amount of carotenoids: stepwise multiple linear regression (SMLR), published spectral indices, band combination indices, and partial least square regression (PLSR). Results show that maximum sensitivity of reflectance to variation in different units of measurement of carotenoids was found in the green region at 515–550 nm, and at 715 nm and 750 nm regions in the far-red wavelengths. The predictive accuracies of Car (g/m2), Car (μg/cm2) and Car (mg/g) were tested on a validation data set and the results show that the highest R2 values between estimations and observations were 0.468 for Car (g/m2), 0.563 for Car (μg/cm2), and 0.456 for Car (mg/g), with relative root mean square error (RMSE%, RMSE/mean) of 48.72%, 22.07% and 21.07%, respectively. Compared to Car (g/m2) and Car (mg/g), the model performance indices for Car (μg/cm2) show a high degree of consistency among the R2 values and RMSE% and MAE% values. Further comparison were performed among the estimation accuracies of different unit carotenoids and among the different approaches used in the study by a paired-t-test. The results indicate that although the best estimation results for Car (μg/cm2) and Car (mg/g) were both obtained based on PLSR, they can be estimated by all four adopted methods without significant differences (P > 0.1). Whereas for Car (g/m2), the best estimation results were obtained based on published vegetation indices CIred-edge, which were significantly better than the estimation results based on SMLR (P < 0.000). In summary, the results of this study show that even the carotenoids expressed on concentration (mg/g) or content (μg/cm2) basis at leaf level can be estimated with the same prediction accuracies to the carotenoids expressed as a mass per unit surface area (g/m2) at canopy level using reflectance measurement at canopy level.  相似文献   

16.
The invasion by Striga in most cereal crop fields in Africa has posed a significant threat to food security and has caused substantial socioeconomic losses. Hyperspectral remote sensing is an effective means to discriminate plant species, providing possibilities to track such weed invasions and improve precision agriculture. However, essential baseline information using remotely sensed data is missing, specifically for the Striga weed in Africa. In this study, we investigated the spectral uniqueness of Striga compared to other co-occurring maize crops and weeds. We used the in-situ FieldSpec® Handheld 2™ analytical spectral device (ASD), hyperspectral data and their respective narrow-band indices in the visible and near infrared (VNIR) region of the electromagnetic spectrum (EMS) and four machine learning discriminant algorithms (i.e. random forest: RF, linear discriminant analysis: LDA, gradient boosting: GB and support vector machines: SVM) to discriminate among different levels of Striga (Striga hermonthica) infestations in maize fields in western Kenya. We also tested the utility of Sentinel-2 waveband configurations to map and discriminate Striga infestation in heterogenous cereal crop fields. The in-situ hyperspectral reflectance data were resampled to the spectral waveband configurations of Sentinel-2 using published spectral response functions. We sampled and detected seven Striga infestation classes based on three flowering Striga classes (low, moderate and high) against two background endmembers (soil and a mixture of maize and other co-occurring weeds). A guided regularized random forest (GRRF) algorithm was used to select the most relevant hyperspectral wavebands and vegetation indices (VIs) as well as for the resampled Sentinel-2 multispectral wavebands for Striga infestation discrimination. The performance of the four discriminant algorithms was compared using classification accuracy assessment metrics. We were able to positively discriminate Striga from the two background endmembers i.e. soil and co-occurring vegetation (maize and co-occurring weeds) based on the few GRRF selected hyperspectral vegetation indices and the GRRF selected resampled Sentinel-2 multispectral bands. RF outperformed all the other discriminant methods and produced the highest overall accuracy of 91% and 85%, using the hyperspectral and resampled Sentinel-2 multispectral wavebands, respectively, across the four different discriminant models tested in this study. The class with the highest detection accuracy across all the four discriminant algorithms, was the “exclusively maize and other co-occurring weeds” (>70%). The GRRF reduced the dimensionality of the hyperspectral data and selected only 9 most relevant wavebands out of 750 wavebands, 6 VIs out of 15 and 6 out of 10 resampled Sentinel-2 multispectral wavebands for discriminating among the Striga and co-occurring classes. Resampled Sentinel-2 multispectral wavebands 3 (green) and 4 (red) were the most crucial for Striga detection. The use of the most relevant hyperspectral features (i.e. wavebands and VIs) significantly (p ≤ 0.05) increased the overall classification accuracy and Kappa scores (±5% and ±0.2, respectively) in all the machine learning discriminant models. Our results show the potential of hyperspectral, resampled Sentinel-2 multispectral datasets and machine learning discriminant algorithms as a tool to accurately discern Striga in heterogenous maize agro-ecological systems.  相似文献   

17.
Statistical and physical models have seldom been compared in studying grasslands. In this paper, both modeling approaches are investigated for mapping leaf area index (LAI) in a Mediterranean grassland (Majella National Park, Italy) using HyMap airborne hyperspectral images. We compared inversion of the PROSAIL radiative transfer model with narrow band vegetation indices (NDVI-like and SAVI2-like) and partial least squares regression (PLS). To assess the performance of the investigated models, the normalized RMSE (nRMSE) and R2 between in situ measurements of leaf area index and estimated parameter values are reported. The results of the study demonstrate that LAI can be estimated through PROSAIL inversion with accuracies comparable to those of statistical approaches (R2 = 0.89, nRMSE = 0.22). The accuracy of the radiative transfer model inversion was further increased by using only a spectral subset of the data (R2 = 0.91, nRMSE = 0.18). For the feature selection wavebands not well simulated by PROSAIL were sequentially discarded until all bands fulfilled the imposed accuracy requirements.  相似文献   

18.
  相似文献   

19.
The presence of salt in the soil profile negatively affects the growth and development of vegetation. As a result, the spectral reflectance of vegetation canopies varies for different salinity levels. This research was conducted to (1) investigate the capability of satellite-based hyperspectral vegetation indices (VIs) for estimating soil salinity in agricultural fields, (2) evaluate the performance of 21 existing VIs and (3) develop new VIs based on a combination of wavelengths sensitive for multiple stresses and find the best one for estimating soil salinity. For this purpose a Hyperion image of September 2, 2010, and data on soil salinity at 108 locations in sugarcane (Saccharum officina L.) fields were used. Results show that soil salinity could well be estimated by some of these VIs. Indices related to chlorophyll absorption bands or based on a combination of chlorophyll and water absorption bands had the highest correlation with soil salinity. In contrast, indices that are only based on water absorption bands had low to medium correlations, while indices that use only visible bands did not perform well. From the investigated indices the optimized soil-adjusted vegetation index (OSAVI) had the strongest relationship (R2 = 0.69) with soil salinity for the training data, but it did not perform well in the validation phase. The validation procedure showed that the new salinity and water stress indices (SWSI) implemented in this study (SWSI-1, SWSI-2, SWSI-3) and the Vogelmann red edge index yielded the best results for estimating soil salinity for independent fields with root mean square errors of 1.14, 1.15, 1.17 and 1.15 dS/m, respectively. Our results show that soil salinity could be estimated by satellite-based hyperspectral VIs, but validation of obtained models for independent data is essential for selecting the best model.  相似文献   

20.
Information about pigment and water contents provides comprehensive insights for evaluating photosynthetic potential and activity of agricultural crops. In this study, we present the concept of using spectral integral ratios (SIR) to retrieve three biochemical traits, namely chlorophyll a and b (Cab), carotenoids (Ccx), and water (Cw) content, simultaneously from hyperspectral measurements in the wavelength range 460−1100 nm. The SIR concept is based on automatic separation of respective absorption features through local peak and intercept analysis between log-transformed reflectance and convex hulls. The algorithm was tested on two synthetically established databases using a physiologically constrained look-up-table (LUT) generated by (i) the leaf optical properties model PROSPECT and (ii) the canopy radiative transfer model (RTM) PROSAIL. LUT constraints were realized based on natural Ccx-Cab relations and green peak locations identified in the leaf optical database ANGERS. Linear regression between obtained SIRs and model parameters resulted in coefficients of determination (R²) of 0.66 (i and ii) for Ccx, R2 = 0.85 (i) and 0.53 (ii) for Cab, and R2 = 0.97 (i) and 0.67 (ii) for Cw, respectively. Using the model established from the PROSPECT LUT, leaf level validation was carried out based on ANGERS data with reasonable results both in terms of goodness of fit and root mean square error (RMSE) (Ccx: R2 = 0.86, RMSE = 2.1 μg cm−2; Cab: R2 = 0.67, RMSE = 12.5 μg cm-2; Cw: R2 = 0.89, RMSE = 0.007 cm). The algorithm was applied to airborne spectrometric HyMap data acquired on 12th July 2003 in Barrax, Spain and to AVIRIS-NG data recorded on 2nd July 2018 southwest of Munich, Germany. Mapping of the SIR results as multiband images (3-segment SIR) allows for intuitive visualization of dominant absorptions with respect to the three considered biochemical variables. Barrax in situ validation using linear regression models derived from PROSAIL LUT showed satisfactory results regarding Cab (R2 = 0.84; RMSE = 9.06 μg cm-2) and canopy water content (CWC, R2 = 0.70; RMSE = 0.05 cm). Retrieved Ccx values were reasonable according to Cab-Ccx-dependence plausibility analysis. Hence, the presented SIR algorithm allows for computationally efficient and RTM supported robust retrievals of the two most important vegetation pigments as well as of water content and is ready to be applied on satellite imaging spectroscopy data available in the near future. The algorithm is publicly available as an interface supported tool within the 'Agricultural Applications' of the EnMAP-Box 3 hyperspectral remote sensing software suite.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号