A framework for determining the total salt content of soil profiles using time-series Sentinel-2 images and a random forest-temporal convolution network

Geoderma ◽  
2022 ◽  
Vol 409 ◽  
pp. 115656
Author(s):  
Nan Wang ◽  
Jie Peng ◽  
Jie Xue ◽  
Xianglin Zhang ◽  
Jingyi Huang ◽  
...  
Keyword(s):  
Time Series ◽  
Random Forest ◽  
Salt Content ◽  
Soil Profiles ◽  
Total Salt Content ◽  
Sentinel 2

scholarly journals ROTATION FORESTS AND RANDOM FOREST CLASSIFIERS FOR MONITORING OF VEGETATION IN PAYS DE BREST (FRANCE)

2020 ◽  
Vol XLIII-B3-2020 ◽  
pp. 727-732
Author(s):  
S. Niculescu ◽  
J. Xia ◽  
D. Roberts ◽  
A. Billey
Keyword(s):  
Remote Sensing ◽  
Time Series ◽  
Random Forest ◽  
Canonical Correlation ◽  
Growing Season ◽  
Radar Images ◽  
Using Data ◽  
Source Of Information ◽  
Forest Rotation ◽  
Sentinel 2

Abstract. Remote sensing is a potentially very useful source of information for spatial monitoring of natural or cultivated vegetation. The latest advances, in particular the arrival of new image acquisition programs, are changing the temporal approach to monitoring vegetation. The latest European satellites launched, delivering an image every 5 days for each point on the globe, allow the end of a growing season to be monitored. The main objective of this work is to identify and map the vegetation in the Pays de Brest area by using a multi sensors stacking of Sentinel-1 and Sentinel-2 satellites data via Random Forest, Rotation forests (RoF) and Canonical Correlation Forests (CCFs). RoF and CCF create diverse base learners using data transformation and subset features. Twenty four radar images and optical dataa representing different dates in 2017 were processed in time series stacks. The results of RoF and CCF were compared with the ones of RF.

scholarly journals Using Sentinel-1 and Sentinel-2 Time Series for Slangbos Mapping in the Free State Province, South Africa

2021 ◽  
Vol 13 (17) ◽  
pp. 3342
Author(s):  
Marcel Urban ◽  
Konstantin Schellenberg ◽  
Theunis Morgenthal ◽  
Clémence Dubois ◽  
Andreas Hirner ◽  
...  
Keyword(s):  
South Africa ◽  
Time Series ◽  
Random Forest ◽  
Expert Knowledge ◽  
Arid Ecosystems ◽  
Free State ◽  
Time Step ◽  
Free State Province ◽  
Sentinel 2

Increasing woody cover and overgrazing in semi-arid ecosystems are known to be the major factors driving land degradation. This study focuses on mapping the distribution of the slangbos shrub (Seriphium plumosum) in a test region in the Free State Province of South Africa. The goal of this study is to monitor the slangbos encroachment on cultivated land by synergistically combining Synthetic Aperture Radar (SAR) (Sentinel-1) and optical (Sentinel-2) Earth observation information. Both optical and radar satellite data are sensitive to different vegetation properties and surface scattering or reflection mechanisms caused by the specific sensor characteristics. We used a supervised random forest classification to predict slangbos encroachment for each individual crop year between 2015 and 2020. Training data were derived based on expert knowledge and in situ information from the Department of Agriculture, Land Reform and Rural Development (DALRRD). We found that the Sentinel-1 VH (cross-polarization) and Sentinel-2 SAVI (Soil Adjusted Vegetation Index) time series information have the highest importance for the random forest classifier among all input parameters. The modelling results confirm the in situ observations that pastures are most affected by slangbos encroachment. The estimation of the model accuracy was accomplished via spatial cross-validation (SpCV) and resulted in a classification precision of around 80% for the slangbos class within each time step.

Pantauan perubahan tutupan padang lamun menggunakan citra Sentinel-2 time-series di wilayah pesisir Pulau Derawan

2019 ◽  
Author(s):  
M. Afif Fauzan ◽  
Hartono ◽  
Pramaditya Wicaksono
Keyword(s):  
Time Series ◽  
Maximum Likelihood ◽  
Random Forest ◽  
Standard Error ◽  
Sentinel 2

Pemantauan kondisi lamun penting untuk dilakukan terutama pada wilayah yang terdapat kecenderungan mengalami tekanan. Pada penelitian ini, delapan citra penginderaan jauh Sentinel-2 MSI time-series digunakan untuk mengidentifikasi perubahan persentase tutupan lamun pada tahun 2016 hingga 2017, serta mengetahui kemampuan algoritma klasifikasi dan regresi sederhana yang diterapkan pada citra Sentinel-2 MSI dalam memetakan dan memantau perubahan lamun dari waktu ke waktu. Penelitian ini dilakukan di wilayah pesisir Pulau Derawan, Berau, Kalimantan Timur, Indonesia, di mana keberlanjutan ekosistem padang lamun terancam oleh peningkatan aktivitas pariwisata dan overgrazing oleh penyu hijau. Hasil penelitian menunjukkan persentase tutupan di wilayah pesisir Pulau Derawan bervariasi dari waktu ke waktu. Terdapat pola perubahan musiman dengan tren penurunan yang terjadi pada rentang waktu 2016 hingga 2017. Dibandingkan dengan algoritma klasifikasi berbasis statistik Maximum Likelihood, algoritma klasifikasi pembelajaran mesin Random Forest mampu memetakan distribusi lamun secara lebih baik dengan akurasi pemetaan mencapai 93%. Dalam mengestimasi persentase tutupan secara kontinyu, reflektansi saluran hijau dari citra Sentinel-2 MSI ditemukan sebagai prediktor terbaik dengan koefisien determinasi (R2) 0,61 dan standard error of estimate (SE) 17%.

scholarly journals A Combined Random Forest and OBIA Classification Scheme for Mapping Smallholder Agriculture at Different Nomenclature Levels Using Multisource Data (Simulated Sentinel-2 Time Series, VHRS and DEM)

2017 ◽  
Vol 9 (3) ◽  
pp. 259 ◽  
Author(s):  
Valentine Lebourgeois ◽  
Stéphane Dupuy ◽  
Élodie Vintrou ◽  
Maël Ameline ◽  
Suzanne Butler ◽  
...  
Keyword(s):  
Time Series ◽  
Random Forest ◽  
Classification Scheme ◽  
Smallholder Agriculture ◽  
Sentinel 2

scholarly journals Lowland Rice Mapping in Sédhiou Region (Senegal) Using Sentinel 1 and Sentinel 2 Data and Random Forest

2020 ◽  
Vol 12 (20) ◽  
pp. 3403 ◽  
Author(s):  
Edoardo Fiorillo ◽  
Edmondo Di Giuseppe ◽  
Giacomo Fontanelli ◽  
Fabio Maselli
Keyword(s):  
Time Series ◽  
Random Forest ◽  
Land Cover ◽  
Technical Assistance ◽  
Lowland Rice ◽  
Ratio Estimator ◽  
Study Region ◽  
Ground Sample ◽  
Ndvi Time Series ◽  
Sentinel 2

In developing countries, information on the area and spatial distribution of paddy rice fields is an essential requirement for ensuring food security and facilitating targeted actions of both technical assistance and restoration of degraded production areas. In this study, Sentinel 1 (S1) and Sentinel 2 (S2) imagery was used to map lowland rice crop areas in the Sédhiou region (Senegal) for the 2017, 2018, and 2019 growing seasons using the Random Forest (RF) algorithm. Ground sample datasets were annually collected (416, 455, and 400 samples) for training and testing yearly RF classification. A procedure was preliminarily applied to process S2 scenes and yield a normalized difference vegetation index (NDVI) time series less affected by clouds. A total of 93 predictors were calculated from S2 NDVI time series and S1 vertical transmit–horizontal receive (VH) and vertical transmit–vertical receive (VV) backscatters. Guided regularized random forest (GRRF) was used to deal with the arising multicollinearity and identify the most important predictors. The RF classifier was then applied to the selected predictors. The algorithm predicted the five land cover types present in the test areas, with a maximum accuracy of 87% and kappa coefficient of 0.8 in 2019. The broad land cover maps identified around 12,500 (2017), 13,800 (2018), and 12,800 (2019) ha of lowland rice crops. The study highlighted a partial difficulty of the classifier to distinguish rice from natural herbaceous vegetation (NHV) due to similar temporal patterns and high intra-class variability. Moreover, the results of this investigation indicated that S2-derived predictors provided more valuable information compared to VV and VH backscatter-derived predictors, but a combination of radar and optical imagery always outperformed a classification based on single-sensor inputs. An example is finally provided that illustrates how the maps obtained can be combined with ground observations through a ratio estimator in order to yield a statistically sound prediction of rice area all over the study region.

scholarly journals Using Sentinel-1 and Sentinel-2 Time Series for Slangbos Encroachment Mapping in the Free State Province, South Africa

2021 ◽  
Author(s):  
Marcel Urban ◽  
Konstantin Schellenberg ◽  
Theunis Morgenthal ◽  
Clèmence Dubois ◽  
Andreas Hirner ◽  
...  
Keyword(s):  
South Africa ◽  
Time Series ◽  
Random Forest ◽  
Southern Africa ◽  
Vegetation Index ◽  
Free State ◽  
Time Step ◽  
Free State Province ◽  
Woody Cover ◽  
Sentinel 2

<p>Increasing woody cover and overgrazing in semi-arid ecosystems are known to be major factors driving land degradation. During the last decades woody cover encroachment has increased over large areas in southern Africa inducing environmental, land cover as well as land use changes. </p><p>The goal of this study is to synergistically combine SAR (Sentinel-1) and optical (Sentinel-2) earth observation information to monitor the slangbos encroachment on arable land in the Free State province, South Africa, between 2015 and 2020. Both, optical and radar satellite data are sensitive to different land surface and vegetation properties caused by sensor specific scattering or reflection mechanisms they rely on. </p><p>This study focuses on mapping the slangbos aka bankrupt bush (Seriphium plumosum) encroachment in a selected test region in the Free State province of South Africa. Though being indigenous to South Africa, the slangbos has been documented to be the main encroacher on the grassvelds (South African grassland biomes) and thrive in poorly maintained cultivated lands. The shrub reaches a height and diameter of up to 0.6 m and the root system reaches a depth of up to 1.8 m. Slangbos has small light green leaves unpalatable to grazers due to their high oil content and is better adapted to long dry periods compared to grass communities.</p><p>We used the random forest approach to predict slangbos encroachment for each individual crop year between 2015 and 2020. Training data were based on expert knowledge and field information from the Department of Agriculture, Forestry and Fisheries (DAFF). Several input variables have been tested according to their model performance, e.g. backscatter, backscatter ratio, interferometric coherence as well as optical indices (e.g. NDVI (Normalized Difference Vegetation Index), SAVI (Soil Adjusted Vegetation Index), EVI (Enhanced Vegetation Index), etc.). We found that the Sentinel-1 VH backscatter (vertical–horizontal/cross-polarization) and the Sentinel-2 SAVI time series information have the highest importance for the random forest classifier among all input parameters. The estimation of the model accuracy was accomplished via spatial-cross validation and resulted in an overall accuracy of above 80 % for each time step, with the slangbos class being close to or above 90 %. </p><p>Currently we are developing a prototype application to be tested in cooperation with local stakeholders to bring this approach to the farmers level. Once field work in southern Africa is possible again, further ground truthing and interaction with farmers will be carried out.</p>

Titration of sulphates and lead using lead ion selective electrode

1981 ◽  
Vol 46 (2) ◽  
pp. 368-376 ◽  
Author(s):  
Josef Veselý
Keyword(s):  
Ionic Strength ◽  
Electrode Surface ◽  
Salt Content ◽  
Ion Selective Electrode ◽  
Lead Ion ◽  
Selective Electrode ◽  
Limit Of Determination ◽  
Total Salt Content ◽  
Automatic Titration

Titration of sulphates with lead perchlorate employing lead ion selective electrode indication was studied using additions of various organic solvents at different pH' and ionic strength values. As the optimum emerged systems with 60-70% 1,4-dioxane, pH' 5.3-5.6. After dehydration with sodium hydroxide, dioxane must be freed from the electrode surface-oxidizing impurities by their reduction with sodium metal and subsequent distillation. The method was applied to determination of sulphates in mountain spring waters. Units of ppm can be determined; the limit of determination, however, depends considerably on the content of dioxane, total salt content in the sample, and speed of the semi-automatic titration. Lead can be determined with EDTA in concentrations down to c(Pb2+) = 5 . 10-6 mol l-1.

Sign in / Sign up

Export Citation Format

Share Document