scholarly journals Mapping Seasonal Agricultural Land Use Types Using Deep Learning on Sentinel-2 Image Time Series

2021 ◽  
Vol 13 (2) ◽  
pp. 289
Author(s):  
Misganu Debella-Gilo ◽  
Arnt Kristian Gjertsen
Keyword(s):  
Land Use ◽  
Time Series ◽  
Deep Learning ◽  
Agricultural Land ◽  
Satellite Image ◽  
Agricultural Land Use ◽  
Monitoring Method ◽  
Multiple Observations ◽  
Land Use Types ◽  
Sentinel 2

The size and location of agricultural fields that are in active use and the type of use during the growing season are among the vital information that is needed for the careful planning and forecasting of agricultural production at national and regional scales. In areas where such data are not readily available, an independent seasonal monitoring method is needed. Remote sensing is a widely used tool to map land use types, although there are some limitations that can partly be circumvented by using, among others, multiple observations, careful feature selection and appropriate analysis methods. Here, we used Sentinel-2 satellite image time series (SITS) over the land area of Norway to map three agricultural land use classes: cereal crops, fodder crops (grass) and unused areas. The Multilayer Perceptron (MLP) and two variants of the Convolutional Neural Network (CNN), are implemented on SITS data of four different temporal resolutions. These enabled us to compare twelve model-dataset combinations to identify the model-dataset combination that results in the most accurate predictions. The CNN is implemented in the spectral and temporal dimensions instead of the conventional spatial dimension. Rather than using existing deep learning architectures, an autotuning procedure is implemented so that the model hyperparameters are empirically optimized during the training. The results obtained on held-out test data show that up to 94% overall accuracy and 90% Cohen’s Kappa can be obtained when the 2D CNN is applied on the SITS data with a temporal resolution of 7 days. This is closely followed by the 1D CNN on the same dataset. However, the latter performs better than the former in predicting data outside the training set. It is further observed that cereal is predicted with the highest accuracy, followed by grass. Predicting the unused areas has been found to be difficult as there is no distinct surface condition that is common for all unused areas.

scholarly journals Sentinel-2 Based Temporal Detection of Agricultural Land Use Anomalies in Support of Common Agricultural Policy Monitoring

2018 ◽  
Vol 7 (10) ◽  
pp. 405 ◽  
Author(s):  
Urška Kanjir ◽  
Nataša Đurić ◽  
Tatjana Veljanovski
Keyword(s):  
Land Use ◽  
Time Series ◽  
Agricultural Policy ◽  
Common Agricultural Policy ◽  
Vegetation Index ◽  
Normalized Difference Vegetation Index ◽  
Agricultural Land ◽  
Agricultural Land Use ◽  
Land Use Control ◽  
Sentinel 2

The European Common Agricultural Policy (CAP) post-2020 timeframe reform will reshape the agriculture land use control procedures from a selected risk fields-based approach into an all-inclusive one. The reform fosters the use of Sentinel data with the objective of enabling greater transparency and comparability of CAP results in different Member States. In this paper, we investigate the analysis of a time series approach using Sentinel-2 images and the suitability of the BFAST (Breaks for Additive Season and Trend) Monitor method to detect changes that correspond to land use anomaly observations in the assessment of agricultural parcel management activities. We focus on identifying certain signs of ineligible (inconsistent) use in permanent meadows and crop fields in one growing season, and in particular those that can be associated with time-defined greenness (vegetation vigor). Depending on the requirements of the BFAST Monitor method and currently time-limited Sentinel-2 dataset for the reliable anomaly study, we introduce customized procedures to support and verify the BFAST Monitor anomaly detection results using the analysis of NDVI (Normalized Difference Vegetation Index) object-based temporal profiles and time-series standard deviation output, where geographical objects of interest are parcels of particular land use. The validation of land use candidate anomalies in view of land use ineligibilities was performed with the information on declared land annual use and field controls, as obtained in the framework of subsidy granting in Slovenia. The results confirm that the proposed combined approach proves efficient to deal with short time series and yields high accuracy rates in monitoring agricultural parcel greenness. As such it can already be introduced to help the process of agricultural land use control within certain CAP activities in the preparation and adaptation phase.

scholarly journals Comparing Sentinel-1 and -2 Data and Indices for Agricultural Land Use Monitoring

2020 ◽  
Vol 12 (18) ◽  
pp. 2919
Author(s):  
Ann-Kathrin Holtgrave ◽  
Norbert Röder ◽  
Andrea Ackermann ◽  
Stefan Erasmi ◽  
Birgit Kleinschmit
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Vegetation Index ◽  
Agricultural Land ◽  
Optical Data ◽  
Agricultural Land Use ◽  
Land Use Type ◽  
Auxiliary Data ◽  
Land Use Types ◽  
Sentinel 2

Agricultural vegetation development and harvest date monitoring over large areas requires frequent remote sensing observations. In regions with persistent cloud coverage during the vegetation season this is only feasible with active systems, such as SAR, and is limited for optical data. To date, optical remote sensing vegetation indices are more frequently used to monitor agricultural vegetation status because they are easily processed, and the characteristics are widely known. This study evaluated the correlations of three Sentinel-2 optical indices with Sentinel-1 SAR indices over agricultural areas to gain knowledge about their relationship. We compared Sentinel-2 Normalized Difference Vegetation Index, Normalized Difference Water Index, and Plant Senescence Radiation Index with Sentinel-1 SAR VV and VH backscatter, VH/VV ratio, and Sentinel-1 Radar Vegetation Index. The study was conducted on 22 test sites covering approximately 35,000 ha of four different main European agricultural land use types, namely grassland, maize, spring barley, and winter wheat, in Lower Saxony, Germany, in 2018. We investigated the relationship between Sentinel-1 and Sentinel-2 indices for each land use type considering three phenophases (growing, green, senescence). The strength of the correlations of optical and SAR indices differed among land use type and phenophase. There was no generic correlation between optical and SAR indices in our study. However, when the data were split by land use types and phenophases, the correlations increased remarkably. Overall, the highest correlations were found for the Radar Vegetation Index and VH backscatter. Correlations for grassland were lower than for the other land use types. Adding auxiliary data to a multiple linear regression analysis revealed that, in addition to land use type and phenophase information, the lower quartile and median SAR values per field, and a spatial variable, improved the models. Other auxiliary data retrieved from a digital elevation model, Sentinel-1 orbit direction, soil type information, and other SAR values had minor impacts on the model performance. In conclusion, despite the different nature of the signal generation, there were distinct relationships between optical and SAR indices which were independent of environmental variables but could be stratified by land use type and phenophase. These relationships showed similar patterns across different test sites. However, a regional clustering of landscapes would significantly improve the relationships.

scholarly journals Responses of the electron transfer capacity of soil humic substances to agricultural land-use types

RSC Advances ◽  
2018 ◽  
Vol 8 (57) ◽  
pp. 32588-32596 ◽  
Author(s):  
Beidou Xi ◽  
Zhurui Tang ◽  
Jie Jiang ◽  
Wenbing Tan ◽  
Caihong Huang ◽  
...  
Keyword(s):  
Land Use ◽  
Electron Transfer ◽  
Humic Substances ◽  
Agricultural Land ◽  
Agricultural Land Use ◽  
Chemical Structures ◽  
Land Use Types ◽  
Electron Transfer Capacity

Agricultural land-use types could affect the transformation and decomposition of HS in soils, and thus further change the intrinsic chemical structures associated with ETC.

Determination of Drought Threshold for Agricultural Land-use using Satellite Image Analysis Techniques

2020 ◽  
Author(s):  
Jieun Kim ◽  
Jaehyung Yu ◽  
Sang Kee Seo ◽  
Jin-Hee Baek ◽  
Byung Chil Jeon
Keyword(s):  
Remote Sensing ◽  
Land Use ◽  
Near Infrared ◽  
Agricultural Land ◽  
Irrigation Management ◽  
Satellite Image ◽  
Agricultural Drought ◽  
Agricultural Land Use ◽  
Landsat 8 ◽  
Eastern Area

<p>The climate change causes major problems in natural disasters such as storms and droughts and has significant impacts on agricultural activities. Especially, global warming changed crops cultivated causing changes in agricultural land-use, and droughts along with land-use change accompanied serious problems in irrigation management. Moreover, it is very problematic to detect drought impacted areas with field survey and it burdens irrigation management. In South Korea, drought in 2012 occurred in western area while 2015 drought occurred in eastern area. The drought cycle in Korea is irregular but the drought frequency has shown an increasing pattern. Remote sensing approaches has been used as a solution to detect drought areas in agricultural land-use and many approaches has been introduced for drought monitoring. This study introduces remote sensing approaches to detect agricultural drought by calculation of local threshold associated with agricultural land-use. We used Landsat-8 satellite images for drought and non-drought years, and Vegetation Health Index(VHI) was calculated using red, near-infrared, and thermal-infrared bands. The comparative analysis of VHI values for the same agricultural land-use between drought year and non-drought year derived the threshold values for each type of land-use. The results showed very effective detection of drought impacted areas showing distinctive differences in VHI value distributions between drought and non-drought years.</p>

Validation of SWEEP for Contrasting Agricultural Land Use Types in the Tarim Basin

Soil Science ◽  
2014 ◽  
Vol 179 (9) ◽  
pp. 433-445 ◽  
Author(s):  
Huawei Pi ◽  
Gary Feng ◽  
Brenton S. Sharratt ◽  
Xinhu Li ◽  
Zehao Zheng
Keyword(s):  
Land Use ◽  
Tarim Basin ◽  
Agricultural Land ◽  
Agricultural Land Use ◽  
Land Use Types

scholarly journals Classifying multiyear agricultural land use data from Mato Grosso using time-series MODIS vegetation index data

2013 ◽  
Vol 130 ◽  
pp. 39-50 ◽  
Author(s):  
J. Christopher Brown ◽  
Jude H. Kastens ◽  
Alexandre Camargo Coutinho ◽  
Daniel de Castro Victoria ◽  
Christopher R. Bishop
Keyword(s):  
Land Use ◽  
Time Series ◽  
Vegetation Index ◽  
Agricultural Land ◽  
Agricultural Land Use ◽  
Mato Grosso ◽  
Index Data

scholarly journals Harmonized in situ JECAM datasets for agricultural land use mapping and monitoring in tropical countries

2021 ◽  
Author(s):  
Audrey Jolivot ◽  
Valentine Lebourgeois ◽  
Mael Ameline ◽  
Valérie Andriamanga ◽  
Beatriz Bellón ◽  
...  
Keyword(s):  
Land Use ◽  
Agricultural Land ◽  
Satellite Image ◽  
Farming Systems ◽  
Agricultural Land Use ◽  
In Situ Data ◽  
Agricultural Census ◽  
Crop Types ◽  
The Tropics

Abstract. The availability of crop type reference datasets for satellite image classification is very limited for complex agricultural systems as observed in developing and emerging countries. Indeed, agricultural land use is very dynamic, agricultural census are often poorly georeferenced, and crop types are difficult to photo-interpret directly from satellite imagery. In this paper, we present nine datasets collected in a standardized manner between 2013 and 2020 in seven tropical and subtropical countries within the framework of the international JECAM (Joint Experiment for Crop Assessment and Monitoring) initiative. These quality-controlled datasets are distinguished by in situ data collected at field scale by local experts, with precise geographic coordinates, and following a common protocol. Altogether, the datasets completed 27 074 polygons (20 257 crop and 6 817 non-crop) documented by detailed keywords. These datasets can be used to produce and validate agricultural land use maps in the tropics, but also, to assess the performances and the robustness of classification methods of cropland and crop types/practices in a large range of tropical farming systems. The dataset is available at https://doi.org/10.18167/DVN1/P7OLAP.

scholarly journals USING LANDSAT 8 IMAGE TIME SERIES FOR CROP MAPPING IN A REGION OF CERRADO, BRAZIL

2016 ◽  
Vol XLI-B8 ◽  
pp. 845-850 ◽  
Author(s):  
H. Bendini ◽  
I. D. Sanches ◽  
T. S. Körting ◽  
L. M. G. Fonseca ◽  
A. J. B. Luiz ◽  
...  
Keyword(s):  
Land Use ◽  
Time Series ◽  
Vegetation Index ◽  
Agricultural Land ◽  
Vegetation Indices ◽  
Agricultural Land Use ◽  
Landsat 8 ◽  
Land Use Classification ◽  
Crop Mapping ◽  
Phenological Metrics

The objective of this research is to classify agricultural land use in a region of the Cerrado (Brazilian Savanna) biome using a time series of Enhanced Vegetation Index (EVI) from Landsat 8 OLI. Phenological metrics extracted from EVI time series, a Random Forest algorithm and data mining techniques are used in the process of classification. The area of study is a region in the Cerrado in a region of the municipality of Casa Branca, São Paulo state, Brazil. The results are encouraging and demonstrate the potential of phenological parameters obtained from time series of OLI vegetation indices for agricultural land use classification.

Sign in / Sign up

Export Citation Format

Share Document