Virtual Issue

农业生态环境-遥感合辑Agro-ecosystem & Environment—Romote sensing

Default Latest Most Read

Please wait a minute... For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails Select Soil temperature estimation at different depths, using remotely-sensed data HUANG Ran, HUANG Jian-xi, ZHANG Chao, MA Hong-yuan, ZHUO Wen, CHEN Ying-yi, ZHU De-hai, Qingling WU, Lamin R. MANSARAY 2020, 19 (1): 277-290.   DOI: 10.1016/S2095-3119(19)62657-2 Abstract （83）      PDF in ScienceDirect       Soil temperatures at different depths down the soil profile are important agro-meteorological indicators which are necessary for ecological modeling and precision agricultural activities.  In this paper, using time series of soil temperature (ST) measured at different depths (0, 5, 10, 20, and 40 cm) at agro-meteorological stations in northern China as reference data, ST was estimated from land surface temperature (LST) and normalized difference vegetation index (NDVI) derived from AQUA/TERRA MODIS data, and solar declination (Ds) in univariate and multivariate linear regression models.  Results showed that when daytime LST is used as predictor, the coefficient of determination (R2) values decrease from the 0 cm layer to the 40 cm layer.  Additionally, with the use of nighttime LST as predictor, the R2 values were relatively higher at 5, 10 and 15 cm depths than those at 0, 20 and 40 cm depths.  It is further observed that the multiple linear regression models for soil temperature estimation outperform the univariate linear regression models based on the root mean squared errors (RMSEs) and R2.  These results have demonstrated the potential of MODIS data in tandem with the Ds parameter for soil temperature estimation at the upper layers of the soil profile where plant roots grow in.  To the best of our knowledge, this is the first attempt at the synergistic use of Reference | Related Articles | Metrics Select Mapping the fallowed area of paddy fields on Sanjiang Plain of Northeast China to assist water security assessments LUO Chong, LIU Huan-jun, FU Qiang, GUAN Hai-xiang, YE Qiang, ZHANG Xin-le, KONG Fan-chang 2020, 19 (7): 1885-1896.   DOI: 10.1016/S2095-3119(19)62871-6 Abstract （115）      PDF in ScienceDirect       Rice growth requires a large amount of water, and planting rice will increase the contradiction between supply and demand of water resources.  Paddy field fallowing is important for the sustainable development of an agricultural region, but it remains a great challenge to accurately and quickly monitor the extent and area of fallowed paddy fields.  Paddy fields have unique physical features associated with paddy rice during the flooding and transplanting phases.  By comparing the differences in phenology before and after paddy field fallowing, we proposed a phenology-based fallowed paddy field mapping algorithm.  We used the Google Earth Engine (GEE) cloud computing platform and Landsat 8 images to extract the fallowed paddy field area on Sanjiang Plain of China in 2018.  The results indicated that the Landsat8, GEE, and phenology-based fallowed paddy field mapping algorithm can effectively support the mapping of fallowed paddy fields on Sanjiang Plain of China.  Based on remote sensing monitoring, the total fallowed paddy field area of Sanjiang Plain is 91 543 ha.  The resultant fallowed paddy field map is of high accuracy, with a producer (user) accuracy of 83% (81%), based on validation using ground-truth samples.  The Landsat-based map also exhibits high consistency with the agricultural statistical data.  We estimated that paddy field fallowing reduced irrigation water by 384–521 million cubic meters on Sanjiang Plain in 2018.  The research results can support subsidization grants for fallowed paddy fields, the evaluation of fallowed paddy field effects and improvement in subsequent fallowed paddy field policy in the future.    Reference | Related Articles | Metrics Select Early-season crop type mapping using 30-m reference time series HAO Peng-yu, TANG Hua-jun, CHEN Zhong-xin, MENG Qing-yan, KANG Yu-peng 2020, 19 (7): 1897-1911.   DOI: 10.1016/S2095-3119(19)62812-1 Abstract （105）      PDF in ScienceDirect       Early-season crop type mapping could provide important information for crop growth monitoring and yield prediction, but the lack of ground-surveyed training samples is the main challenge for crop type identification.  Although reference time series based method (RBM) has been proposed to identify crop types without the use of ground-surveyed training samples, the methods are not suitable for study regions with small field size because the reference time series are mainly generated using data set with low spatial resolution.  As the combination of Landsat data and Sentinel-2 data could increase the temporal resolution of 30-m image time series, we improved the RBM by generating reference normalized difference vegetation index (NDVI)/enhanced vegetation index (EVI) time series at 30-m resolution (30-m RBM) using both Landsat and Sentinel-2 data, then tried to estimate the potential of the reference NDVI/EVI time series for crop identification at early season.  As a test case, we tried to use the 30-m RBM to identify major crop types in Hengshui, China at early season of 2018, the results showed that when the time series of the entire growing season were used for classification, overall classification accuracies of the 30-m RBM were higher than 95%, which were similar to the accuracies acquired using the ground-surveyed training samples.  In addition, cotton, spring maize and summer maize distribution could be accurately generated 8, 6 and 8 weeks before their harvest using the 30-m RBM; but winter wheat can only be accurately identified around the harvest time phase.  Finally, NDVI outperformed EVI for crop type classification as NDVI had better separability for distinguishing crops at the green-up time phases.  Comparing with the previous RBM, advantage of 30-m RBM is that the method could use the samples of the small fields to generate reference time series and process image time series with missing value for early-season crop classification; while, samples collected from multiple years should be further used so that the reference time series could contain more crop growth conditions.   Reference | Related Articles | Metrics Select A case-based method of selecting covariates for digital soil mapping LIANG Peng, QIN Cheng-zhi, ZHU A-xing, HOU Zhi-wei, FAN Nai-qing, WANG Yi-jie 2020, 19 (8): 2127-2136.   DOI: 10.1016/S2095-3119(19)62857-1 Abstract （91）      PDF in ScienceDirect       Selecting a proper set of covariates is one of the most important factors that influence the accuracy of digital soil mapping (DSM).  The statistical or machine learning methods for selecting DSM covariates are not available for those situations with limited samples.  To solve the problem, this paper proposed a case-based method which could formalize the covariate selection knowledge contained in practical DSM applications.  The proposed method trained Random Forest (RF) classifiers with DSM cases extracted from the practical DSM applications and then used the trained classifiers to determine whether each one potential covariate should be used in a new DSM application.  In this study, we took topographic covariates as examples of covariates and extracted 191 DSM cases from 56 peer-reviewed journal articles to evaluate the performance of the proposed case-based method by Leave-One-Out cross validation.  Compared with a novices’ commonly-used way of selecting DSM covariates, the proposed case-based method improved more than 30% accuracy according to three quantitative evaluation indices (i.e., recall, precision, and F1-score).  The proposed method could be also applied to selecting the proper set of covariates for other similar geographical modeling domains, such as landslide susceptibility mapping, and species distribution modeling.   Reference | Related Articles | Metrics Select Comparison of machine learning algorithms for mapping mango plantations based on Gaofen-1 imagery LUO Hong-xia, DAI Sheng-pei, LI Mao-fen, LIU En-ping, ZHENG Qian, HU Ying-ying, YI Xiao-ping 2020, 19 (11): 2815-2828.   DOI: 10.1016/S2095-3119(20)63208-7 Abstract （80）      PDF in ScienceDirect       Mango is a commercial crop on Hainan Island, China, that is cultivated to develop the tropical rural economy.  The development of accurate and up-to-date maps of the spatial distribution of mango plantations is necessary for agricultural monitoring and decision management by the local government.  Pixel-based and object-oriented image analysis methods for mapping mango plantations were compared using two machine learning algorithms (support vector machine (SVM) and Random Forest (RF)) based on Chinese high-resolution Gaofen-1 (GF-1) imagery in parts of Hainan Island.  To assess the importance of different features on classification accuracy, a combined layer of four original bands, 32 gray-level co-occurrence (GLCM) texture indices, and 10 vegetation indices were used as input features.  Then five different sets of variables (5, 10, 20, and 30 input variables and all 46 variables) were classified with the two machine learning algorithms at object-based level.  Results of the feature optimization suggested that homogeneity and variance were very important variables for distinguishing mango plantations patches.  The object-based classifiers could significantly improve overall accuracy between 2–7% when compared to pixel-based classifiers.  When there were 5 and 10 input variables, SVM showed higher classification accuracy than RF, and when the input variables exceeded 20, RF showed better performances.  After the accuracy achieved saturation points, there were only slightly classification accuracy improvements along with the numbers of feature increases for both of SVM and RF classifiers.  The results indicated that GF-1 imagery can be successfully applied to mango plantation mapping in tropical regions, which would provide a useful framework for accurate tropical agriculture land management.  Reference | Related Articles | Metrics Select From statistics to grids: A two-level model to simulate crop pattern dynamics XIA Tian, WU Wen-bin, ZHOU Qing-bo, Peter H. VERBURG, YANG Peng, HU Qiong, YE Li-ming, ZHU Xiao-juan 2022, 21 (6): 1786-1789.   DOI: 10.1016/S2095-3119(21)63713-9 Abstract （166）      PDF in ScienceDirect       Crop planting patterns are an important component of agricultural land systems.  These patterns have been significantly changed due to the combined impacts of climatic changes and socioeconomic developments.  However, the extent of these changes and their possible impacts on the environment, terrestrial landscapes and rural livelihoods are largely unknown due to the lack of spatially explicit datasets including crop planting patterns.  To fill this gap, this study proposes a new method for spatializing statistical data to generate multitemporal crop planting pattern datasets.  This method features a two-level model that combines a land-use simulation and a crop pattern simulation.  The output of the first level is the spatial distribution of the cropland, which is then used as the input for the second level, which allocates crop censuses to individual gridded cells according to certain rules.  The method was tested using data from 2000 to 2019 from Heilongjiang Province, China, and was validated using remote sensing images.  The results show that this method has high accuracy for crop area spatialization.  Spatial crop pattern datasets over a given time period can be important supplementary information for remote sensing and thus support a wide range of application in agricultural land systems. Reference | Related Articles | Metrics Select Monthly composites from Sentinel-1 and Sentinel-2 images for regional major crop mapping with Google Earth Engine LUO Chong, LIU Huan-jun, LU Lü-ping, LIU Zheng-rong, KONG Fan-chang, ZHANG Xin-le 2021, 20 (7): 1944-1957.   DOI: 10.1016/S2095-3119(20)63329-9 Abstract （83）      PDF in ScienceDirect       Rapid and accurate access to large-scale, high-resolution crop-type distribution maps is important for agricultural management and sustainable agricultural development.  Due to the limitations of remote sensing image quality and data processing capabilities, large-scale crop classification is still challenging.  This study aimed to map the distribution of crops in Heilongjiang Province using Google Earth Engine (GEE) and Sentinel-1 and Sentinel-2 images.  We obtained Sentinel-1 and Sentinel-2 images from all the covered study areas in the critical period for crop growth in 2018 (May to September), combined monthly composite images of reflectance bands, vegetation indices and polarization bands as input features, and then performed crop classification using a Random Forest (RF) classifier.  The results show that the Sentinel-1 and Sentinel-2 monthly composite images combined with the RF classifier can accurately generate the crop distribution map of the study area, and the overall accuracy (OA) reached 89.75%.  Through experiments, we also found that the classification performance using time-series images is significantly better than that using single-period images.  Compared with the use of traditional bands only (i.e., the visible and near-infrared bands), the addition of shortwave infrared bands can improve the accuracy of crop classification most significantly, followed by the addition of red-edge bands.  Adding common vegetation indices and Sentinel-1 data to the crop classification improved the overall classification accuracy and the OA by 0.2 and 0.6%, respectively, compared to using only the Sentinel-2 reflectance bands.  The analysis of timeliness revealed that when the July image is available, the increase in the accuracy of crop classification is the highest.  When the Sentinel-1 and Sentinel-2 images for May, June, and July are available, an OA greater than 80% can be achieved.  The results of this study are applicable to large-scale, high-resolution crop classification and provide key technologies for remote sensing-based crop classification in small-scale agricultural areas. Reference | Related Articles | Metrics Select Winter wheat yield estimation based on assimilated Sentinel-2 images with the CERES-Wheat model LIU Zheng-chun, WANG Chao, BI Ru-tian, ZHU Hong-fen, HE Peng, JING Yao-dong, YANG Wu-de 2021, 20 (7): 1958-1968.   DOI: 10.1016/S2095-3119(20)63483-9 Abstract （81）      PDF in ScienceDirect       Assimilating Sentinel-2 images with the CERES-Wheat model can improve the precision of winter wheat yield estimates at a regional scale.  To verify this method, we applied the ensemble Kalman filter (EnKF) to assimilate the leaf area index (LAI) derived from Sentinel-2 data and simulated by the CERES-Wheat model.  From this, we obtained the assimilated daily LAI during the growth stage of winter wheat across three counties located in the southeast of the Loess Plateau in China: Xiangfen, Xinjiang, and Wenxi.  We assigned LAI weights at different growth stages by comparing the improved analytic hierarchy method, the entropy method, and the normalized combination weighting method, and constructed a yield estimation model with the measurements to accurately estimate the yield of winter wheat.  We found that the changes of assimilated LAI during the growth stage of winter wheat strongly agreed with the simulated LAI.  With the correction of the derived LAI from the Sentinel-2 images, the LAI from the green-up stage to the heading–filling stage was enhanced, while the LAI decrease from the milking stage was slowed down, which was more in line with the actual changes of LAI for winter wheat.  We also compared the simulated and derived LAI and found the assimilated LAI had reduced the root mean square error (RMSE) by 0.43 and 0.29 m2 m–2, respectively, based on the measured LAI.  The assimilation improved the estimation accuracy of the LAI time series.  The highest determination coefficient (R2) was 0.8627 and the lowest RMSE was 472.92 kg ha–1 in the regression of the yields estimated by the normalized weighted assimilated LAI method and measurements.  The relative error of the estimated yield of winter wheat in the study counties was less than 1%, suggesting that Sentinel-2 data with high spatial-temporal resolution can be assimilated with the CERES-Wheat model to obtain more accurate regional yield estimates. Reference | Related Articles | Metrics Select Simple method for extracting the seasonal signals of photochemical reflectance index and normalized difference vegetation index measured using a spectral reflectance sensor Jae-Hyun RYU, Dohyeok OH, Jaeil CHO 2021, 20 (7): 1969-1986.   DOI: 10.1016/S2095-3119(20)63410-4 Abstract （44）      PDF in ScienceDirect       A spectral reflectance sensor (SRS) fixed on the near-surface ground was developed to support the continuous monitoring of vegetation indices such as the normalized difference vegetation index (NDVI) and photochemical reflectance index (PRI).  NDVI is useful for indicating crop growth/phenology, whereas PRI was developed for observing physiological conditions.  Thus, the seasonal change patterns of NDVI and PRI are two valuable pieces of information in a crop-monitoring system.  However, capturing the seasonal patterns is considered challenging because the vegetation index values estimated by the reflection from vegetation are often governed by meteorological conditions, such as solar irradiance and precipitation.  Further, unlike growth/phenology, the physiological condition has diurnal changes as well as seasonal characteristics.  This study proposed a novel filtering method for extracting the seasonal signals of SRS-based NDVI and PRI in paddy rice, barley, and garlic.  First, the measurement accuracy of SRSs was compared with handheld spectrometers, and the R2 values between the two devices were 0.96 and 0.81 for NDVI and PRI, respectively.  Second, the experimental study of threshold criteria with respect to meteorological variables (i.e., insolation, cloudiness, sunshine duration, and precipitation) was conducted, and sunshine duration was the most useful one for excluding distorted values of the vegetation indices.  After data processing based on sunshine duration, the R2 values between the measured vegetation indices and the extracted seasonal signals of vegetation indices increased by approximately 0.002–0.004 (NDVI) and 0.065–0.298 (PRI) on the three crops, and the seasonal signals of vegetation indices became noticeably improved.  This method will contribute to an agricultural monitoring system by identifying the seasonal changes in crop growth and physiological conditions. Reference | Related Articles | Metrics Select An entirely new approach based on remote sensing data to calculate the nitrogen nutrition index of winter wheat ZHAO Yu, WANG Jian-wen, CHEN Li-ping, FU Yuan-yuan, ZHU Hong-chun, FENG Hai-kuan, XU Xin-gang, LI Zhen-hai 2021, 20 (9): 2535-2551.   DOI: 10.1016/S2095-3119(20)63379-2 Abstract （158）      PDF in ScienceDirect       The nitrogen nutrition index (NNI) is a reliable indicator for diagnosing crop nitrogen (N) status.  However, there is currently no specific vegetation index for the NNI inversion across multiple growth periods.  To overcome the limitations of the traditional direct NNI inversion method (NNIT1) of the vegetation index and traditional indirect NNI inversion method (NNIT2) by inverting intermediate variables including the aboveground dry biomass (AGB) and plant N concentration (PNC), this study proposed a new NNI remote sensing index (NNIRS).  A remote-sensing-based critical N dilution curve (Nc_RS) was set up directly from two vegetation indices and then used to calculate NNIRS.  Field data including AGB, PNC, and canopy hyperspectral data were collected over four growing seasons (2012–2013 (Exp.1), 2013–2014 (Exp. 2), 2014–2015 (Exp. 3), 2015–2016 (Exp. 4)) in Beijing, China.  All experimental datasets were cross-validated to each of the NNI models (NNIT1, NNIT2 and NNIRS).  The results showed that: (1) the NNIRS models were represented by the standardized leaf area index determining index (sLAIDI) and the red-edge chlorophyll index (CIred edge) in the form of NNIRS=CIred edge/(a×sLAIDIb), where “a” equals 2.06, 2.10, 2.08 and 2.02 and “b” equals 0.66, 0.73, 0.67 and 0.62 when the modeling set data came from Exp.1/2/4, Exp.1/2/3, Exp.1/3/4, and Exp.2/3/4, respectively; (2) the NNIRS models achieved better performance than the other two NNI revised methods, and the ranges of R2 and RMSE were 0.50–0.82 and 0.12–0.14, respectively; (3) when the remaining data were used for verification, the NNIRS models also showed good stability, with RMSE values of 0.09, 0.18, 0.13 and 0.10, respectively.  Therefore, it is concluded that the NNIRS method is promising for the remote assessment of crop N status. Reference | Related Articles | Metrics Select Effects of land use/cover change (LUCC) on the spatiotemporal variability of precipitation and temperature in the Songnen Plain, China CHU Xiao-lei, LU Zhong, WEI Dan, LEI Guo-ping 2022, 21 (1): 235-248.   DOI: 10.1016/S2095-3119(20)63495-5 Abstract （126）      PDF in ScienceDirect       Understanding the effects of land use/cover change (LUCC) on regional climate is critical for achieving land use system sustainability and global climate change mitigation.  However, the quantitative analysis of the contribution of LUCC to the changes of climatic factors, such as precipitation & temperature (P&T), is lacking.  In this study, we combined statistical methods and the gravity center model simulation to quantify the effects of long-term LUCC on P&T in the Songnen Plain (SNP) of Northeast China from 1980–2018.  The results showed the spatiotemporal variability of LUCC. For example, paddy field had the largest increase (15 166.43 km2) in the SNP, followed by dry land, while wetland had the largest decrease (19 977.13 km2) due to the excessive agricultural utilization and development.  Annual average precipitation decreased at a rate of –9.89 mm per decade, and the warming trends were statistically significant with an increasing rate of 0.256°C per decade in this region since 1980.  The model simulation revealed that paddy field, forestland, and wetland had positive effects on precipitation, which caused their gravity centers to migrate towards the same direction accompanied by the center of precipitation gravity, while different responses were seen for building land, dry land and unused land.  These results indicated that forestland had the largest influence on the increase of precipitation compared with the other land use types.  The responses in promoting the temperature increase differed significantly, being the highest in building land, and the lowest in forestland.  In general, the analysis of regional-scale LUCC showed a significant reduction of wetland, and the increases in building land and cropland contributed to a continuous drying and rapid warming in the SNP. Reference | Related Articles | Metrics Select Predicting soil depth in a large and complex area using machine learning and environmental correlations LIU Feng, YANG Fei, ZHAO Yu-guo, ZHANG Gan-lin, LI De-cheng 2022, 21 (8): 2422-2434.   DOI: 10.1016/S2095-3119(21)63692-4 Abstract （108）      PDF in ScienceDirect       Soil depth is critical for eco-hydrological modeling, carbon storage calculation and land evaluation.  However, its spatial variation is poorly understood and rarely mapped.  With a limited number of sparse samples, how to predict soil depth in a large area of complex landscapes is still an issue.  This study constructed an ensemble machine learning model, i.e., quantile regression forest, to quantify the relationship between soil depth and environmental conditions.  The model was then combined with a rich set of environmental covariates to predict spatial variation of soil depth and straightforwardly estimate the associated predictive uncertainty in the 140 000 km2 Heihe River basin of northwestern China.  A total of 275 soil depth observation points and 26 covariates were used.  The results showed a model predictive accuracy with coefficient of determination (R2) of 0.587 and root mean square error (RMSE) of 2.98 cm (square root scale), i.e., almost 60% of soil depth variation explained.  The resulting soil depth map clearly exhibited regional patterns as well as local details.  Relatively deep soils occurred in low lying landscape positions such as valley bottoms and plains while shallow soils occurred in high and steep landscape positions such as hillslopes, ridges and terraces.  The oases had much deeper soils than outside semi-desert areas, the middle of an alluvial plain had deeper soils than its margins, and the middle of a lacustrine plain had shallower soils than its margins.  Large predictive uncertainty mainly occurred in areas with a lack of soil survey points.  Both pedogenic and geomorphic processes contributed to the shaping of soil depth pattern of this basin but the latter was dominant.  This findings may be applicable to other similar basins in cold and arid regions around the world. Reference | Related Articles | Metrics