基于支持向量机的作物叶绿素含量反演模型

针对现有研究在准确估算叶绿素含量方面的不足,该文运用粒子群优化算法和支持向量机构建叶片尺度作物叶绿素含量高光谱反演模型:利用PROSPECT模型模拟作物光谱,并运用所对应的叶绿素含量建立训练数据集,然后采用粒子群优化算法支持向量机学习训练数据集,最后建立实测叶片叶绿素含量估测模型。研究结果表明,粒子群优化算法和支持向量机构建的反演模型能准确预测作物的叶绿素含量,能够解决小样本作物采样点情况下叶绿素含量反演问题,可以作为作物叶绿素含量估测的参考方法。     

估算混合植被叶绿素含量的理想波段分析

应用Lopex数据库评价了19个波谱指数对物种的敏感性, 分析了叶绿素含量与波谱反射率以及波谱导数的相关性, 目的在于探寻对叶绿素含量变化的敏感性, 对物种和叶片结构变化不敏感的理想波段, 应用大尺度遥感数据估算混合植被冠层叶绿素含量。分析结果表明：红边指数对混合植被的叶绿素含量具有较好的指示作用;估算冠层叶绿素含量的理想波段为698—710nm附近较窄的波段范围;对于波谱导数, 估算混合植被叶绿素含量的理想波段范围为720—735nm和535—550nm附近波谱导数。     

Remote estimation of crop and grass chlorophyll and nitrogen content using red-edge bands on Sentinel-2 and -3

Sentinel-2 is planned for launch in 2014 by the European Space Agency and it is equipped with the Multi Spectral Instrument (MSI), which will provide images with high spatial, spectral and temporal resolution. It covers the VNIR/SWIR spectral region in 13 bands and incorporates two new spectral bands in the red-edge region, which can be used to derive vegetation indices using red-edge bands in their formulation. These are particularly suitable for estimating canopy chlorophyll and nitrogen (N) content. This band setting is important for vegetation studies and is very similar to the ones of the Ocean and Land Colour Instrument (OLCI) on the planned Sentinel-3 satellite and the Medium Resolution Imaging Spectrometer (MERIS) on Envisat, which operated from 2002 to early 2012. This paper focuses on the potential of Sentinel-2 and Sentinel-3 in estimating total crop and grass chlorophyll and N content by studying in situ crop variables and spectroradiometer measurements obtained for four different test sites. In particular, the red-edge chlorophyll index (CI_red-edge), the green chlorophyll index (CI_green) and the MERIS terrestrial chlorophyll index (MTCI) were found to be accurate and linear estimators of canopy chlorophyll and N content and the Sentinel-2 and -3 bands are well positioned for deriving these indices. Results confirm the importance of the red-edge bands on particularly Sentinel-2 for agricultural applications, because of the combination with its high spatial resolution of 20 m.     

Regional yield estimation for winter wheat with MODIS-NDVI data in Shandong, China

The significance of crop yield estimation is well known in agricultural management and policy development at regional and national levels. The primary objective of this study was to test the suitability of the method, depending on predicted crop production, to estimate crop yield with a MODIS-NDVI-based model on a regional scale. In this paper, MODIS-NDVI data, with a 250 m resolution, was used to estimate the winter wheat (Triticum aestivum L.) yield in one of the main winter-wheat-growing regions. Our study region is located in Jining, Shandong Province. In order to improve the quality of remote sensing data and the accuracy of yield prediction, especially to eliminate the cloud-contaminated data and abnormal data in the MODIS-NDVI series, the Savitzky–Golay filter was applied to smooth the 10-day NDVI data. The spatial accumulation of NDVI at the county level was used to test its relationship with winter wheat production in the study area. A linear regressive relationship between the spatial accumulation of NDVI and the production of winter wheat was established using a stepwise regression method. The average yield was derived from predicted production divided by the growing acreage of winter wheat on a county level. Finally, the results were validated by the ground survey data, and the errors were compared with the errors of agro-climate models. The results showed that the relative errors of the predicted yield using MODIS-NDVI are between −4.62% and 5.40% and that whole RMSE was 214.16 kg ha⁻¹ lower than the RMSE (233.35 kg ha⁻¹) of agro-climate models in this study region. A good predicted yield data of winter wheat could be got about 40 days ahead of harvest time, i.e. at the booting-heading stage of winter wheat. The method suggested in this paper was good for predicting regional winter wheat production and yield estimation.     

冬小麦叶面积指数的高光谱估算模型研究

本文以山东禹城为研究区,利用地面实测光谱数据,探讨不同植被指数和红边参数建立高光谱模型反演冬小麦叶面积指数的精度.通过逐波段分析计算了4种植被指数( NDVI、RVI、SAVI、EVI),结合同步观测LAI数据,确定反演叶面积指数的最优波段;计算了5种常用的高光谱植被指数MCARI、MCARI2、OSAVI、MTVI2、MSAVI2,同时利用4种常用方法计算红边位置和红谷,与实测LAI进行回归分析,比较植被指数和红边参数模型对冬小麦LAI的估测精度.结果表明各因子与LAI均具有较高的相关性,整个研究区归一化植被指数具有最高的反演精度,确定了估算冬小麦LAI的最优模型,并使用独立的LAI观测数据     

Wheat growth profile: satellite monitoring and crop yield modelling

The most important advantage of the low resolution National Oceanic and Atmospheric Administration’s Advanced Very High Resolution Radiometer (NOAA AVHRR) data is its high temporal frequency and high radiometric sensitivity which helps in vegetation detection in the visible and near-infrared spectral regions. In areas where most of the crop cultivation is in large contiguous areas, and if the AVHRR data are selected for time period such that the crop of interest is well discriminated from other crops, these data can be used for monitoring vegetative growth and condition very effectively. The present study deals with the application of AVHRR data for the monitoring of the wheat crop in its seventeen main growing districts of the Rajasthan state. The fourteen date AVHRR data covering the entire growth period have been used to generate the normalized difference vegetation index (NDV1) growth profile for the crop by masking the non-crop pixels following the two-date NDVI change method. The growth profile parameters and other derived parameters, such as post-anthesis senescence rate and areas under the entire growth profile or under selected growth periods have been related to the district average wheat yield through statistical regression models. Various methods adopted for wheat pixels masking have been critically evaluated. It is found that the wheat yield can be predicted well by the area under the profile in different growth periods.     

Pre-harvest wheat yield prediction using agromet-spectral-trend-yield models for hoshiarpur and rupnagar districts of punjab

Wheat yield prediction using different agrometeorological indices, spectral index (NDVI, Normalized Difference Vegetation Index) and trend predicted yield (TPY) were developed in Hoshiarpur and Rupnagar districts of Punjab. On the basis of examination of Correlation Coefficients (R), Standard Error of Estimate (SEOE) and Relative Deviation (RD) values resulted from different agromet models, the best agromet subset were selected as Minimum Temperature (T_min), Maximum Temperature (T_max) and accumulated Heliothermal Units (HTU) in case of Hoshiarpur district and Minimum Temperature (T--_min), accumulated Temperature Difference (TD) and accumulated Pan Evaporation (E) for Rupnagar district at reproductive stage (2^nd week of March) of wheat. It was found that Agromet-Spectral-Trend-Yield model could explain 96 % (SEOE = 87 kg/ha) and 91 % (SEOE = 146 kg/ha) of wheat yield variations for Hoshiarpur and Rupnagar districts, respectively.     

Crop growth modelling and crop yield forecasting using satellite-derived meteorological inputs

Distributed crop simulation models are typically confronted with considerable uncertainty in weather variables. In this paper the use of MeteoSat-derived meteorological products to replace weather variables interpolated from weather stations (temperature, reference evapotranspiration and radiation) is explored. Simulations for winter-wheat were carried for Spain, Poland and Belgium using both interpolated and MeteoSat-derived weather variables. The results were spatially aggregated to national and regional level and were evaluated by comparing the simulation results of both approaches and by assessing the relationships with crop yield statistics over the periods 1995–2003 from EUROSTAT. The results indicate that potential crop yield can be simulated well using MeteoSat-derived meteorological variables, but that water-stress hardly occurs in the water-limited simulations. This is caused by a difference in reference evapotranspiration which was 20–30% smaller in case of MeteoSat. As a result, the simulations using MeteoSat-derived meteorological variables performed considerably poorer in a regression analyses with crop yield statistics on national and regional level. Our results indicate that a recalibration of the model parameters is necessary before the MeteoSat-derived meteorological variables can be used operationally in the system.     

不同方法对冬小麦地块级估产的适用性研究

为了探究不同估产模型对冬小麦估产的精度和适用性,提高像元级和地块级冬小麦估产精度。利用机器学习方法支持向量机（SVM）模型、随机森林（RF）模型和深度学习方法长短期记忆（LSTM）模型,对冬小麦进行产量预估。结果表明：在像元级上,LSTM模型、RF模型估产精度高于SVM模型,LSTM模型不仅能够表征作物在生育期的生长变化,还能降低人为因素干扰,估产结果更加客观真实,而SVM模型、RF模型易受到特征共线性和过拟合的影响,因此SVM模型、RF模型更适用于区域性小范围估产。在地块级上,SVM模型、RF模型和LSTM模型地块级估产精度比像元级估产精度均有提高,且LSTM模型估产精度明显高于SVM模型和RF模型,因此LSTM模型更适用于地块级估产,且LSTM模型泛化能力强、普适性高,适用于大范围农作物估产。     

遥感技术在主要粮食作物估产中的应用

文章分析了国内外遥感技术在主要粮食作物估产中应用现状,探讨了遥感技术在作物估产领域的研究进展,研究了作物气候产量预报模型、遗传算法结合神经网络模型、基于人机交互的反演模型、基于决策树分类的县域估产模型、单产估测模型、基于SCE_UA算法的CERES_Wheat模型、雷达遥感估产模型等在我国主要农作物估产中的应用;分析表明遥感关键技术及模型选择为农作物估产精度的提高提供了重要的技术支持.最后对作物估产遥感技术发展趋势及农业信息化相关技术做了展望,指出综合遥感与计算机技术开发自动化系统、推进物联网与遥感技术结合等问题,是进一步的研究趋势.     

Spectral wheat growth profile in Punjab using IRS WiFS data

A functional form of crop spectral profile suggested by Badhwar was applied to district-wise wheat Normalised Difference Vegetation Index (NDVI) values relatively normalised by Pseudo-Invariant Feature (urban and built-up) NDVI values, derived from Wide Field Sensor (WiFS) onboard Indian Remote Sensing Satellites (IRS) for 17 dates during 1999–2000 rabi season. The goodness of overall profile fitting and the three basic parameters i.e., crop emergence date (T_o), and crop specific parameters (a and P) was found to be statistically significant. While a corresponds to profile progressive growth rate, β corresponds to profile decay rate. A comparison with earlier studies in Punjab using NOAA-AVHRR indicated improvement in relation between peak NDVI and wheat yield. The estimated time of spectral emergence and profile-derived peak NDVI follow the observed behaviour of shortened crop pre-anthesis period with delayed sowing.     

Winter wheat yield forecasting in Ukraine based on Earth observation,meteorological data and biophysical models

Ukraine is one of the most developed agriculture countries and one of the biggest crop producers in the world. Timely and accurate crop yield forecasts for Ukraine at regional level become a key element in providing support to policy makers in food security. In this paper, feasibility and relative efficiency of using moderate resolution satellite data to winter wheat forecasting in Ukraine at oblast level is assessed. Oblast is a sub-national administrative unit that corresponds to the NUTS2 level of the Nomenclature of Territorial Units for Statistics (NUTS) of the European Union. NDVI values were derived from the MODIS sensor at the 250 m spatial resolution. For each oblast NDVI values were averaged for a cropland map (Rainfed croplands class) derived from the ESA GlobCover map, and were used as predictors in the regression models. Using a leave-one-out cross-validation procedure, the best time for making reliable yield forecasts in terms of root mean square error was identified. For most oblasts, NDVI values taken in April–May provided the minimum RMSE value when comparing to the official statistics, thus enabling forecasts 2–3 months prior to harvest. The NDVI-based approach was compared to the following approaches: empirical model based on meteorological observations (with forecasts in April–May that provide minimum RMSE value) and WOFOST crop growth simulation model implemented in the CGMS system (with forecasts in June that provide minimum RMSE value). All three approaches were run to produce winter wheat yield forecasts for independent datasets for 2010 and 2011, i.e. on data that were not used within model calibration process. The most accurate predictions for 2010 were achieved using the CGMS system with the RMSE value of 0.3 t ha⁻¹ in June and 0.4 t ha⁻¹ in April, while performance of three approaches for 2011 was almost the same (0.5–0.6 t ha⁻¹ in April). Both NDVI-based approach and CGMS system overestimated winter wheat yield comparing to official statistics in 2010, and underestimated it in 2011. Therefore, we can conclude that performance of empirical NDVI-based regression model was similar to meteorological and CGMS models when producing winter wheat yield forecasts at oblast level in Ukraine 2–3 months prior to harvest, while providing minimum requirements to input datasets.     

Analysis of sorghum yield dependence on crop growth characteristics using noaa-avhrr data

Growth profiles of 1987-88 rabi sorghum crop cultivated in spatially extensive sites in six tehsils of Solapur and Ahmadnagar districts in Maharashtra have been generated using multidate NOAA AVHRR data based on crop growth equation suggested by Badhwar (1980). The sensitive parameters for sorghum yield modelling have been identified. The correlation of final grain yield with growth parameters shows that yield relationship is stronger when logarithmic senescence rate and timeintegrated logarithmic senescence rate are considered as the parameters instead of its value on any day during 30 days senescence period after attaining maximum vegetative cover.     

Development and validation of spectrometeorological yield models of mustard oil seed crop in Rajasthan state

Attempt has been made to develop spectro meteorological yield models using normalized difference vegetation index (NDVI) derived from NOAA AVHRR data over the crop growth period and monthly rainfall data for predicting yield of mustard crop. The AVHRR data spanning seven crop growing seasons, the rain gauze station-level rainfall data and crop yield data determined from crop cutting experiments (CCE) conducted by state Directorate of Economics and Statistics (DES) are the basic input data. A methodology has been developed to normalize the multi-temporal NDVIs for the minimisation of atmospheric effects, which is found to reduce the noise in NDVI due to varying atmospheric conditions from season to season and improve the predictability of statistical multiple linear regression yield models developed for nine geographically large districts of Rajasthan state. The spectro meteorological yield models had been validated by comparing the predicted district level yields with those estimated from the crop cutting experiments.     

A novel combined spectral index for estimating the ratio of carotenoid to chlorophyll content to monitor crop physiological and phenological status

Accurate estimation of the ratio of carotenoid (Car) to chlorophyll (Chl) content is crucial to provide valuable insight into diagnoses of plant physiological and phenological status in crop fields. Studies for assessing the ratio of Car to Chl content have been extensively conducted with semi-empirical approaches using spectral indices. However, spectral indices established in previous studies generally relied on site- or species-specific measured data and these indices typically lacked sufficient estimation accuracy for the ratio of Car to Chl content to be used across various species and under different physiological conditions. In this study, we propose a novel combined carotenoid/chlorophyll ratio index (CCRI) in the form of the carotenoid index (CARI) divided by the red-edge chlorophyll index (CI_red-edge): The value of the index is illustrated using synthetic data simulated from the leaf radiative transfer model PROSPECT-5 and with extensive measured datasets at both the leaf and canopy level from the ANGERS dataset and winter wheat and maize field experiments. Results show that CCRI was the index with the highest correlation with the ratio of Car to Chl content in PROSPECT-5 simulations (R² = 0.99, RRMSE = 8.65%) compared to other spectral indices. Calibration and validation results using the ANGERS and winter wheat leaf level data showed that CCRI achieved accurate estimation of the ratio of Car to Chl content (R² = 0.52, RRMSE = 14.10%). CCRI also showed a good performance (R² = 0.54, RRMSE = 17.08%) for estimation of the ratio of Car to Chl content in both calibration and validation with the winter wheat and maize canopy spectra measured in field experiments. Further investigation of the effect of the correlation between leaf Chl and Car content on the performance of CCRI indicated that variation of the correlation affected the retrieval accuracy of CCRI, and CCRI might not be very sensitive to changes of the ratio of Car to Chl content with low values (<0.10).     

基于RS和GIS的农作物估产方法研究进展

实时获取农作物长势及产量等信息对于现代农业的发展具有重要意义。近年来,随着遥感技术(remote sensing,RS)和地理信息系统(geographic information system,GIS)广泛应用于农作物估产领域,相继出现了一些较为实用的估产方法,主要有结合辅助数据的估产方法、基于植被指数的估产方法、基于特定模型的估产方法和基于农作物估产平台(软件)的开发等。其中,基于植被指数的估产方法又分为单一和多植被指数估产2类方法。在对近年来该领域大量文献深入研究的基础上,着重就几类热点方法展开论述,并对每类方法的优势和缺陷进行了评述,最后对该领域需要进一步研究的方向进行了探讨和展望,以期为后续研究提供参考。     

Spectral signatures of moisture-stressed wheat

One of the important parameters affecting crop yield is the availability of soil moisture to the crop. Lack of it may bring about moisture stress in plants which manifests itself in terms of changes in the spectral reflectance and emittance properties of plants. An experiment involving radiometric measurements over six wheat plots subjected to different irrigation schedules was conducted to test this hypothesis. Vegetation index defined in terms of crop reflectances in 0.6 to 0.7 and 0.8 to 1,1 micrometer bands was found to be a sensitive parameter to distinguish normal plants from moisture-stressed plants. The optimum period for the discrimination of such plants through remote sensing techniques has been indicated to be 45–80 days after sowing. The experiment also demonstrates that yield per unit area is linearly related to the maximum leaf-area index of the crop thus providing a possible method of crop yield prediction.     

Relation of wheat yield with parameters derived from a spectral growth profile

An attempt has been made to generate crop growth profiles using multi-date NOAA AVHRR data of wheat-growing season of 1987–88 for the districts of Punjab and Haryana states of India. A profile model proposed by Badhwar was fitted to the multi-date Normalised Difference Vegetation Index (NDVI) values obtained from geographically referenced samples in each district. A novel approach of deriving a set of physiologically meaningful profile parameters has been outlined and the relation of these parameters with district wheat yields has been studied in order to examine the potential of growth profiles for crop-yield modelling. The parameter ‘area under the profile’ is found to be the best estimator of yield. However, with such a parameter time available for prediction gets reduced. Combination of different profile parameters shows improvement in correlation but lacks the consistency for individual state data.     

LAI and chlorophyll estimation for a heterogeneous grassland using hyperspectral measurements

The study shows that leaf area index (LAI), leaf chlorophyll content (LCC) and canopy chlorophyll content (CCC) can be mapped in a heterogeneous Mediterranean grassland from canopy spectral reflectance measurements. Canopy spectral measurements were made in the field using a GER 3700 spectroradiometer, along with concomitant in situ measurements of LAI and LCC. We tested the utility of univariate techniques involving narrow band vegetation indices and the red edge inflection point, as well as multivariate calibration techniques, including stepwise multiple linear regression and partial least squares regression. Among the various investigated models, CCC was estimated with the highest accuracy (, ). All methods failed to estimate LCC (), while LAI was estimated with intermediate accuracy ( values ranged from 0.49 to 0.69). Compared with narrow band indices and red edge inflection point, stepwise multiple linear regression generally improved the estimation of LAI. The estimations were further improved when partial least squares regression was used. When a subset of wavelengths was analyzed, it was found that partial least squares regression had reduced the error in the retrieved parameters. The results of the study highlight the significance of multivariate techniques, such as partial least squares regression, rather than univariate methods such as vegetation indices in estimating heterogeneous grass canopy characteristics.     

Estimation of winter wheat crop growth parameters using time series Sentinel-1A SAR data

In the present study, Sentinel-1A Synthetic Aperture Radar analysis of time series data at C-band was carried out to estimate the winter wheat crop growth parameters. Five different date images were acquired during January 2015–April 2015 at different growth stages from tillering to ripening in Varanasi district, India. The winter wheat crop parameters, i.e. leaf area index, vegetation water content (VWC), fresh biomass (FB), dry biomass (DB) and plant height (PH) were estimated using random forest regression (RFR), support vector regression (SVR), artificial neural network regression (ANNR) and linear regression (LR) algorithms. The Ground Range Detected products of Interferometric Wide (IW) Swath were used at VV polarization. The three different subplots of 1 m² area were taken for the measurement of crop parameters at every growth stage. In total, 73 samples were taken as the training data-sets and 39 samples were taken as testing data-sets. The highest sensitivity (adj. R^2?=?0.95579) of backscattering with VWC was found using RFR algorithm, whereas the lowest sensitivity (adj. R^2?=?0.66201) was found for the PH using LR algorithm. Overall results indicate more accurate estimation of winter wheat parameters by the RFR algorithm followed by SVR, ANNR and LR algorithms.