Improving the Accuracy of Multiple Algorithms for Crop Classification by Integrating Sentinel-1 Observations with Sentinel-2 Data

The availability of an unprecedented amount of open remote sensing data, such as Sentinel-1 and -2 data within the Copernicus program, has boosted the idea of combining the use of optical and radar data to improve the accuracy of agricultural applications such as crop classification. Sentinel-1’s Synthetic Aperture Radar (SAR) provides co- and cross-polarized backscatter, which offers the opportunity to monitor agricultural crops using radar at high spatial and temporal resolution. In this study, we assessed the potential of integrating Sentinel-1 information (VV and VH backscatter and their ratio VH/VV with Sentinel-2A data (NDVI) to perform crop classification and to define which are the most important input data that provide the most accurate classification results. Further, we examined the temporal dynamics of remote sensing data for cereal, horticultural, and industrial crops, perennials, deciduous trees, and legumes. To select the best SAR input feature, we tried two approaches, one based on classification with only SAR features and one based on integrating SAR with optical data. In total, nine scenarios were tested. Furthermore, we evaluated the performance of 22 nonparametric classifiers on which most of these algorithms had not been tested before with SAR data. The results revealed that the best performing scenario was the one integrating VH and VV with normalized difference vegetation index (NDVI) and cubic support vector machine (SVM) (the kernel function of the classifier is cubic) as the classifier with the highest accuracy among all those tested.

Download Full-text

Detecting Forest Degradation in the Three-North Forest Shelterbelt in China from Multi-Scale Satellite Images

Remote Sensing ◽

10.3390/rs13061131 ◽

2021 ◽

Vol 13 (6) ◽

pp. 1131

Author(s):

Tao Yu ◽

Pengju Liu ◽

Qiang Zhang ◽

Yi Ren ◽

Jingning Yao

Keyword(s):

Remote Sensing ◽

Vegetation Index ◽

Normalized Difference Vegetation Index ◽

Net Primary Production ◽

Remote Sensing Data ◽

Forest Degradation ◽

Observation Data ◽

Area Index ◽

Sensing Data ◽

Multi Scale

Detecting forest degradation from satellite observation data is of great significance in revealing the process of decreasing forest quality and giving a better understanding of regional or global carbon emissions and their feedbacks with climate changes. In this paper, a quick and applicable approach was developed for monitoring forest degradation in the Three-North Forest Shelterbelt in China from multi-scale remote sensing data. Firstly, Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI), Ratio Vegetation Index (RVI), Leaf Area Index (LAI), Fraction of Photosynthetically Active Radiation (FPAR) and Net Primary Production (NPP) from remote sensing data were selected as the indicators to describe forest degradation. Then multi-scale forest degradation maps were obtained by adopting a new classification method using time series MODerate Resolution Imaging Spectroradiometer (MODIS) and Landsat Enhanced Thematic Mapper Plus (ETM+) images, and were validated with ground survey data. At last, the criteria and indicators for monitoring forest degradation from remote sensing data were discussed, and the uncertainly of the method was analyzed. Results of this paper indicated that multi-scale remote sensing data have great potential in detecting regional forest degradation.

Download Full-text

Rapid primary productivity changes in one of the last coastal rainforests: the case of Kahua, Solomon Islands

Environmental Conservation ◽

10.1017/s0376892909990208 ◽

2009 ◽

Vol 36 (3) ◽

pp. 253-260 ◽

Cited By ~ 20

Author(s):

IRENE GARONNA ◽

IOAN FAZEY ◽

MOLLY E. BROWN ◽

NATHALIE PETTORELLI

Keyword(s):

Remote Sensing ◽

Primary Productivity ◽

Vegetation Index ◽

Normalized Difference Vegetation Index ◽

Solomon Islands ◽

Remote Sensing Data ◽

Human Populations ◽

Sensing Data ◽

Relative Contribution ◽

Indirect Impacts

SUMMARYThe growth of human populations has many direct and indirect impacts on tropical forest ecosystems both locally and globally. This is particularly true in the Solomon Islands, where coastal rainforest cover still remains, but where climate change and a growing human population is putting increasing pressure on ecosystems. This study assessed recent primary productivity changes in the Kahua region (Makira, Solomon Islands) using remote sensing data (normalized difference vegetation index, NDVI). In this area, there has been no commercial logging and there is no existing information about the state of the forests. Results indicate that primary productivity has been decreasing in recent years, and that the recent changes are more marked near villages. Multiple factors may explain the reported pattern in primary productivity. The study highlights the need to (1) assess how accurately remote sensing data-based results match field data on the ground; (2) identify the relative contribution of the climatic, socioeconomic and political drivers of such changes; and (3) evaluate how primary productivity changes affect biodiversity level, ecosystem functioning and human livelihoods.

Download Full-text

Analyzing the Relationship between Animal Diversity and the Remote Sensing Vegetation Parameters: The Case of Xinjiang, China

Sustainability ◽

10.3390/su13179897 ◽

2021 ◽

Vol 13 (17) ◽

pp. 9897

Author(s):

Jinhui Wu ◽

Haoxin Li ◽

Huawei Wan ◽

Yongcai Wang ◽

Chenxi Sun ◽

...

Keyword(s):

Remote Sensing ◽

Vegetation Index ◽

Normalized Difference Vegetation Index ◽

Remote Sensing Data ◽

Bird Diversity ◽

Area Index ◽

Sensing Data ◽

Animal Diversity ◽

The Mean ◽

The Impact

An explicit analysis of the impact for the richness of species of the vegetation phenological characteristics calculated from various remote sensing data is critical and essential for biodiversity conversion and restoration. This study collected long-term the Normalized Difference Vegetation Index (NDVI), the Leaf Area Index (LAI), the Fraction of Absorbed Photosynthetically Active Radiation (FAPAR), and the Fractional Vegetation Cover (FVC), and calculated the six vegetation phenological characteristic parameters: the mean of the growing season, the mean of the mature season, the mean of the withered season, the annual difference value, the annual cumulative value, and the annual standard deviation in the Xinjiang Uygur Autonomous Region. The relationships between the vegetation phenological characteristics and the species richness of birds and mammals were analyzed in spatial distribution. The main findings include: (1) The correlation between bird diversity and vegetation factors is greater than that of mammals. (2) For remote sensing data, FAPAR is the most important vegetation parameter for both birds and mammals. (3) For vegetation phenological characteristics, the annual cumulative value of the LAI is the most crucial vegetation phenological parameter for influencing bird diversity distribution, and the annual difference value of the NDVI is the most significant driving factor for mammal diversity distribution.

Download Full-text

Synergistic Use of Multi-Temporal RADARSAT-2 and VENµS Data for Crop Classification Based on 1D Convolutional Neural Network

Remote Sensing ◽

10.3390/rs12050832 ◽

2020 ◽

Vol 12 (5) ◽

pp. 832 ◽

Cited By ~ 1

Author(s):

Chunhua Liao ◽

Jinfei Wang ◽

Qinghua Xie ◽

Ayman Al Baz ◽

Xiaodong Huang ◽

...

Keyword(s):

Neural Network ◽

Remote Sensing ◽

Deep Learning ◽

Convolutional Neural Network ◽

Remote Sensing Data ◽

Support Vector ◽

Learning Methods ◽

Sensing Data ◽

Multi Temporal ◽

Crop Classification

Annual crop inventory information is important for many agriculture applications and government statistics. The synergistic use of multi-temporal polarimetric synthetic aperture radar (SAR) and available multispectral remote sensing data can reduce the temporal gaps and provide the spectral and polarimetric information of the crops, which is effective for crop classification in areas with frequent cloud interference. The main objectives of this study are to develop a deep learning model to map agricultural areas using multi-temporal full polarimetric SAR and multi-spectral remote sensing data, and to evaluate the influence of different input features on the performance of deep learning methods in crop classification. In this study, a one-dimensional convolutional neural network (Conv1D) was proposed and tested on multi-temporal RADARSAT-2 and VENµS data for crop classification. Compared with the Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN) and non-deep learning methods including XGBoost, Random Forest (RF), and Support Vector Machina (SVM), the Conv1D performed the best when the multi-temporal RADARSAT-2 data (Pauli decomposition or coherency matrix) and VENµS multispectral data were fused by the Minimum Noise Fraction (MNF) transformation. The Pauli decomposition and coherency matrix gave similar overall accuracy (OA) for Conv1D when fused with the VENµS data by the MNF transformation (OA = 96.65 ± 1.03% and 96.72 ± 0.77%). The MNF transformation improved the OA and F-score for most classes when Conv1D was used. The results reveal that the coherency matrix has a great potential in crop classification and the MNF transformation of multi-temporal RADARSAT-2 and VENµS data can enhance the performance of Conv1D.

Download Full-text

Soil Moisture Retrieval in Farmland Areas with Sentinel Multi-Source Data Based on Regression Convolutional Neural Networks

Sensors ◽

10.3390/s21030877 ◽

2021 ◽

Vol 21 (3) ◽

pp. 877

Author(s):

Jian Liu ◽

Youshuan Xu ◽

Henghui Li ◽

Jiao Guo

Keyword(s):

Neural Network ◽

Remote Sensing ◽

Soil Moisture ◽

Moisture Content ◽

Soil Moisture Content ◽

Remote Sensing Data ◽

Optimal Combination ◽

Optical Data ◽

Support Vector ◽

Sensing Data

As an important component of the earth ecosystem, soil moisture monitoring is of great significance in the fields of crop growth monitoring, crop yield estimation, variable irrigation, and other related applications. In order to mitigate or eliminate the impacts of sparse vegetation covers in farmland areas, this study combines multi-source remote sensing data from Sentinel-1 radar and Sentinel-2 optical satellites to quantitatively retrieve soil moisture content. Firstly, a traditional Oh model was applied to estimate soil moisture content after removing vegetation influence by a water cloud model. Secondly, support vector regression (SVR) and generalized regression neural network (GRNN) models were used to establish the relationships between various remote sensing features and real soil moisture. Finally, a regression convolutional neural network (CNNR) model is constructed to extract deep-level features of remote sensing data to increase soil moisture retrieval accuracy. In addition, polarimetric decomposition features for real Sentinel-1 PolSAR data are also included in the construction of inversion models. Based on the established soil moisture retrieval models, this study analyzes the influence of each input feature on the inversion accuracy in detail. The experimental results show that the optimal combination of R2 and root mean square error (RMSE) for SVR is 0.7619 and 0.0257 cm3/cm3, respectively. The optimal combination of R2 and RMSE for GRNN is 0.7098 and 0.0264 cm3/cm3, respectively. Especially, the CNNR model with optimal feature combination can generate inversion results with the highest accuracy, whose R2 and RMSE reach up to 0.8947 and 0.0208 cm3/cm3, respectively. Compared to other methods, the proposed algorithm improves the accuracy of soil moisture retrieval from synthetic aperture radar (SAR) and optical data. Furthermore, after adding polarization decomposition features, the R2 of CNNR is raised by 0.1524 and the RMSE of CNNR decreased by 0.0019 cm3/cm3 on average, which means that the addition of polarimetric decomposition features effectively improves the accuracy of soil moisture retrieval results.

Download Full-text

Analisis Tutupan Mangrove Taman Nasional Berbak–Sembilang melalui Citra Landsat-8 dan Pemantauan LAI

Jurnal Kelautan Tropis ◽

10.14710/jkt.v24i3.12278 ◽

2021 ◽

Vol 24 (3) ◽

pp. 393-401

Author(s):

Tengku Zia Ulqodry ◽

Andreas Eko Aprianto ◽

Andi Agussalim ◽

Riris Aryawati ◽

Afan Absori

Keyword(s):

Remote Sensing ◽

Leaf Area Index ◽

Leaf Area ◽

Vegetation Index ◽

Normalized Difference Vegetation Index ◽

Remote Sensing Data ◽

Landsat 8 ◽

Area Index ◽

Sensing Data ◽

Canopy Coverage

Berbak Sembilang National Park of South Sumatra Region (BSNP South Sumatera) is the largest mangrove ecosystem in the western part of Indonesia. Monitoring of mangrove coverage in BSNP South Sumatera carried out using Landsat-8 imagery data based on NDVI values (Normalized Difference Vegetation Index) integrated with mangrove LAI (Leaf Area Index) data. The research purpose was to analyze the mangrove coverage and mapping the density of the mangrove vegetation canopy with the integration of remote sensing data and LAI. This research conducted field survey with LAI measurement of mangrove canopy coverage and integrated with remote sensing data to validate map. The determination and correlation coefficient of NDVI and LAI value of canopy coverage was high (R2 = 0.69 ; r = 83.07).The results of research indicated that the overall distribution of the mangrove area was 94,622.05 ha. The NDVI image integration map with LAI resulted in 4 mangrove canopy density classes consisted of rare canopy (688.80 ha ; 0.73%), moderately dense canopy (1,139.55 ha ; 1.2%), dense canopy (35,003.46 ha ; 37%), and very dense canopy (57,790.20 ha ; 61.07%). Taman Nasional Berbak Sembilang wilayah Sumatera Selatan (TNBS Sumsel) merupakan kawasan ekosistem mangrove terluas di wilayah Indonesia bagian barat. Pemantauan kerapatan kanopi vegetasi mangrove di TNBS Sumsel dilakukan menggunakan data Citra Landsat-8 berdasarkan nilai NDVI (Normalized Difference Vegetation Index) yang diintegrasikan dengan data LAI (Leaf Area Index) mangrove di lapangan. Penelitian ini bertujuan untuk menganalisis tutupan vegetasi mangrove dan memetakan sebaran kerapatan kanopi mangrove dengan integrasi data penginderaan jauh dan LAI. Penelitian ini menggunakan metode pengolahan data survei lapangan dan hasil pengolahan citra satelit. Nilai koefisien determinasi dan korelasi antara nilai NDVI dengan nilai LAI tutupan Kanopi di Lapangan dikategorikan tinggi (R2 = 0,69 ; r = 83,07). Hasil penelitian menunjukkan tutupan mangrove secara keseluruhan seluas 94.622,05 ha. Peta integrasi citra NDVI dengan LAI mangrove di lapangan menghasilkan 4 kelas kerapatan kanopi mangrove yakni kanopi jarang seluas 688,80 ha (0,73%), kanopi sedang seluas 1.139,55 ha (1,2%), kanopi lebat seluas 35.003,46 ha (37%), dan kanopi sangat lebat seluas 57.790,20 ha (61,07%).

Download Full-text

Quantitative Assessment of Desertification in an Arid Oasis Using Remote Sensing Data and Spectral Index Techniques

Remote Sensing ◽

10.3390/rs10121862 ◽

2018 ◽

Vol 10 (12) ◽

pp. 1862 ◽

Cited By ~ 7

Author(s):

Atman Lamqadem ◽

Hafid Saber ◽

Biswajeet Pradhan

Keyword(s):

Remote Sensing ◽

Quantitative Assessment ◽

Vegetation Index ◽

Normalized Difference Vegetation Index ◽

Linear Regression Analysis ◽

Remote Sensing Data ◽

Feature Space ◽

Transformation Method ◽

Sensing Data ◽

Environmental Threat

Desertification is an environmental problem worldwide. Remote sensing data and technique offer substantial information for mapping and assessment of desertification. Desertification is one of the most serious forms of environmental threat in Morocco, especially in the oases in the south-eastern part of the country. This study aims to map the degree of desertification in middle Draa Valley in 2017 using a Sentinel-2 MSI (multispectral instrument) image. Firstly, three indices, namely, tasselled cap brightness (TCB), greenness (TCG) and wetness (TCW) were extracted using the tasselled cap transformation method. Secondly, other indices, such as normalized difference vegetation index (NDVI) and albedo, were retrieved. Thirdly, a linear regression analysis was performed on NDVI–albedo, TCG–TCB and TCW–TCB combinations. Results showed a higher correlation between TCW and TCB (r = −0.812) than with that of the NDVI–albedo (r = −0.50). On the basis of this analysis, a desertification degree index was developed using the TCW–TCB feature space classification. A map of desertification grades was elaborated and divided into five classes, namely, nondesertification, low, moderate, severe and extreme levels. Results indicated that only 6.20% of the study area falls under the nondesertification grade, whereas 26.92% and 32.85% fall under the severe and extreme grades, respectively. The employed method was useful for the quantitative assessment of desertification with an overall accuracy of 93.07%. This method is simple, robust, powerful, and easy to use for the management and protection of the fragile arid and semiarid lands.

Download Full-text

THE UTILIZATION OF REMOTE SENSING DATA TO SUPPORT GREEN OPEN SPACE MAPPING IN JAKARTA, INDONESIA

International Journal of Remote Sensing and Earth Sciences (IJReSES) ◽

10.30536/j.ijreses.2018.v15.a2890 ◽

2019 ◽

Vol 15 (2) ◽

pp. 199

Author(s):

Hana Listi Fitriana ◽

Sayidah Sulma ◽

Nur Febrianti ◽

Jalu Tejo Nugroho ◽

Nanik Suryo Haryani

Keyword(s):

Remote Sensing ◽

Open Space ◽

Vegetation Index ◽

Normalized Difference Vegetation Index ◽

Remote Sensing Data ◽

Landsat 8 ◽

Index Method ◽

Multispectral Data ◽

Sensing Data

Green open space becomes critical in maintaining the balance of the environment and improving the quality of urban living for a healthy life. The use of remote sensing data for calculation of green open space has been done notably using NDVI (Normalized Difference Vegetation Index) method from Landsat 8 and SPOT data. This research aims to calculate the accuracy of the green open space classification from multispectral data of Landsat 8 and SPOT 6 using the NDVI methods. Green open space could be assessed from the value NDVI. The value of NDVI generated from Landsat 8 and SPOT 6’s Red and NIR channels. The accuracy of NDVI values is then examined by comparing with Pleiades data. Pleiades data which has 50 cm panchromatic resolution and 2 m multispectral with 4 bands (B, G, R, NIR) can precisely visualize objects. So, it can be used as the reference in the calculation of the green open space based on NDVI. The results of the accuracy testing of Landsat 8 and SPOT 6 image could be used to identify the green open space by using NDVI SPOT of 6 can increase the accuracy of 5.36% from Landsat 8.

Download Full-text