scholarly journals Comparison of Machine Learning Algorithms for Retrieval of Water Quality Indicators in Case-II Waters: A Case Study of Hong Kong

2019 ◽  
Vol 11 (6) ◽  
pp. 617 ◽  
Author(s):  
Sidrah Hafeez ◽  
Man Wong ◽  
Hung Ho ◽  
Majid Nazeer ◽  
Janet Nichol ◽  
...  
Keyword(s):  
Machine Learning ◽  
Water Quality ◽  
Satellite Data ◽  
Coastal Waters ◽  
Machine Learning Techniques ◽  
Blue Band ◽  
Chl A ◽  
Learning Techniques ◽  
Reflectance Data

Anthropogenic activities in coastal regions are endangering marine ecosystems. Coastal waters classified as case-II waters are especially complex due to the presence of different constituents. Recent advances in remote sensing technology have enabled to capture the spatiotemporal variability of the constituents in coastal waters. The present study evaluates the potential of remote sensing using machine learning techniques, for improving water quality estimation over the coastal waters of Hong Kong. Concentrations of suspended solids (SS), chlorophyll-a (Chl-a), and turbidity were estimated with several machine learning techniques including Artificial Neural Network (ANN), Random Forest (RF), Cubist regression (CB), and Support Vector Regression (SVR). Landsat (5,7,8) reflectance data were compared with in situ reflectance data to evaluate the performance of machine learning models. The highest accuracies of the water quality indicators were achieved by ANN for both, in situ reflectance data (89%-Chl-a, 93%-SS, and 82%-turbidity) and satellite data (91%-Chl-a, 92%-SS, and 85%-turbidity. The water quality parameters retrieved by the ANN model was further compared to those retrieved by “standard Case-2 Regional/Coast Colour” (C2RCC) processing chain model C2RCC-Nets. The root mean square errors (RMSEs) for estimating SS and Chl-a were 3.3 mg/L and 2.7 µg/L, respectively, using ANN, whereas RMSEs were 12.7 mg/L and 12.9 µg/L for suspended particulate matter (SPM) and Chl-a concentrations, respectively, when C2RCC was applied on Landsat-8 data. Relative variable importance was also conducted to investigate the consistency between in situ reflectance data and satellite data, and results show that both datasets are similar. The red band (wavelength ≈ 0.665 µm) and the product of red and green band (wavelength ≈ 0.560 µm) were influential inputs in both reflectance data sets for estimating SS and turbidity, and the ratio between red and blue band (wavelength ≈ 0.490 µm) as well as the ratio between infrared (wavelength ≈ 0.865 µm) and blue band and green band proved to be more useful for the estimation of Chl-a concentration, due to their sensitivity to high turbidity in the coastal waters. The results indicate that the NN based machine learning approaches perform better and, thus, can be used for improved water quality monitoring with satellite data in optically complex coastal waters.

scholarly journals Integrating Satellite and Ground Measurements for Predicting Locations of Extreme Urban Heat

Climate ◽  
2019 ◽  
Vol 7 (1) ◽  
pp. 5 ◽  
Author(s):  
Vivek Shandas ◽  
Jackson Voelkel ◽  
Joseph Williams ◽  
Jeremy Hoffman
Keyword(s):  
Machine Learning ◽  
Satellite Data ◽  
Machine Learning Techniques ◽  
Metropolitan Region ◽  
Landscape Features ◽  
Ambient Temperatures ◽  
Air Temperatures ◽  
Learning Techniques ◽  
Urban Heat

The emergence of urban heat as a climate-induced health stressor is receiving increasing attention among researchers, practitioners, and climate educators. However, the measurement of urban heat poses several challenges with current methods leveraging either ground based, in situ observations, or satellite-derived surface temperatures estimated from land use emissivity. While both techniques contain inherent advantages and biases to predicting temperatures, their integration may offer an opportunity to improve the spatial resolution and global application of urban heat measurements. Using a combination of ground-based measurements, machine learning techniques, and spatial analysis, we addressed three research questions: (1) How much do ambient temperatures vary across time and space in a metropolitan region? (2) To what extent can the integration of ground-based measurements and satellite imagery help to predict temperatures? (3) What landscape features consistently amplify and temper heat? We applied our analysis to the cities of Baltimore, Maryland, and Richmond, Virginia, and the District of Columbia using geocomputational machine learning processes on data collected on days when maximum air temperatures were above the 90th percentile of historic averages. Our results suggest that the urban microclimate was highly variable across all of the cities—with differences of up to 10 °C between coolest and warmest locations at the same time—and that these air temperatures were primarily dependent on underlying landscape features. Additionally, we found that integrating satellite data with ground-based measures provided highly accurate and precise descriptions of temperatures in all three study regions. These results suggest that accurately identifying areas of extreme urban heat hazards for any region is possible through integrating ground-based temperature and satellite data.

Machine Learning techniques for solar irradiation nowcasting: Cloud type classification forecast through satellite data and imagery

2022 ◽  
Vol 305 ◽  
pp. 117834
Author(s):  
Alfredo Nespoli ◽  
Alessandro Niccolai ◽  
Emanuele Ogliari ◽  
Giovanni Perego ◽  
Elena Collino ◽  
...  
Keyword(s):  
Machine Learning ◽  
Satellite Data ◽  
Machine Learning Techniques ◽  
Solar Irradiation ◽  
Cloud Type ◽  
Learning Techniques ◽  
Type Classification

scholarly journals Predicting land deformation by integrating InSAR data and cone penetration testing through machine learning techniques

2020 ◽  
Vol 382 ◽  
pp. 525-529
Author(s):  
Melika Sajadian ◽  
Ana Teixeira ◽  
Faraz S. Tehrani ◽  
Mathias Lemmens
Keyword(s):  
Machine Learning ◽  
Soil Mechanics ◽  
Machine Learning Techniques ◽  
Cone Penetration ◽  
Penetration Testing ◽  
Cone Penetration Testing ◽  
Learning Techniques ◽  
Land Deformation ◽  
Spatio Temporal

Abstract. Built environments developed on compressible soils are susceptible to land deformation. The spatio-temporal monitoring and analysis of these deformations are necessary for sustainable development of cities. Techniques such as Interferometric Synthetic Aperture Radar (InSAR) or predictions based on soil mechanics using in situ characterization, such as Cone Penetration Testing (CPT) can be used for assessing such land deformations. Despite the combined advantages of these two methods, the relationship between them has not yet been investigated. Therefore, the major objective of this study is to reconcile InSAR measurements and CPT measurements using machine learning techniques in an attempt to better predict land deformation.

Experiments on Machine Learning Techniques for Soil Classification Using Sentinel-2 Products

2020 ◽  
Author(s):  
Victor Bacu ◽  
Teodor Stefanut ◽  
Dorian Gorgan
Keyword(s):  
Machine Learning ◽  
High Resolution ◽  
Satellite Data ◽  
Field Measurements ◽  
Soil Classification ◽  
Machine Learning Techniques ◽  
Classification Models ◽  
Spatial Features ◽  
Learning Techniques ◽  
Sentinel 2

<p>Agricultural management relies on good, comprehensive and reliable information on the environment and, in particular, the characteristics of the soil. The soil composition, humidity and temperature can fluctuate over time, leading to migration of plant crops, changes in the schedule of agricultural work, and the treatment of soil by chemicals. Various techniques are used to monitor soil conditions and agricultural activities but most of them are based on field measurements. Satellite data opens up a wide range of solutions based on higher resolution images (i.e. spatial, spectral and temporal resolution). Due to this high resolution, satellite data requires powerful computing resources and complex algorithms. The need for up-to-date and high-resolution soil maps and direct access to this information in a versatile and convenient manner is essential for pedology and agriculture experts, farmers and soil monitoring organizations.</p><p>Unfortunately, the satellite image processing and interpretation are very particular to each area, time and season, and must be calibrated by the real field measurements that are collected periodically. In order to obtain a fairly good accuracy of soil classification at a very high resolution, without using interpolation methods of an insufficient number of measurements, the prediction based on artificial intelligence techniques could be used. The use of machine learning techniques is still largely unexplored, and one of the major challenges is the scalability of the soil classification models toward three main directions: (a) adding new spatial features (i.e. satellite wavelength bands, geospatial parameters, spatial features); (b) scaling from local to global geographical areas; (c) temporal complementarity (i.e. build up the soil description by samples of satellite data acquired along the time, on spring, on summer, in another year, etc.).</p><p>The presentation analysis some experiments and highlights the main issues on developing a soil classification model based on Sentinel-2 satellite data, machine learning techniques and high-performance computing infrastructures. The experiments concern mainly on the features and temporal scalability of the soil classification models. The research is carried out using the HORUS platform [1] and the HorusApp application [2], [3], which allows experts to scale the computation over cloud infrastructure.</p><p> </p><p>References:</p><p>[1] Gorgan D., Rusu T., Bacu V., Stefanut T., Nandra N., “Soil Classification Techniques in Transylvania Area Based on Satellite Data”. World Soils 2019 Conference, 2 - 3 July 2019, ESA-ESRIN, Frascati, Italy (2019).</p><p>[2] Bacu V., Stefanut T., Gorgan D., “Building soil classification maps using HorusApp and Sentinel-2 Products”, Proceedings of the Intelligent Computer Communication and Processing Conference – ICCP, in IEEE press (2019).</p><p>[3] Bacu V., Stefanut T., Nandra N., Rusu T., Gorgan D., “Soil classification based on Sentinel-2 Products using HorusApp application”, Geophysical Research Abstracts, Vol. 21, EGU2019-15746, 2019, EGU General Assembly (2019).</p>

SentiLake - Sentinel-2 satellite data-based service for monitoring of Latvian lakes

2020 ◽  
Author(s):  
Dainis Jakovels ◽  
Agris Brauns ◽  
Jevgenijs Filipovs ◽  
Tuuli Soomets
Keyword(s):  
Water Quality ◽  
Satellite Data ◽  
Ecological Status ◽  
Quality Parameters ◽  
Water Bodies ◽  
Water Quality Parameters ◽  
Chl A ◽  
Regular Monitoring ◽  
Sentinel 2

<p>Lakes and water reservoirs are important ecosystems providing such services as drinking water, recreation, support for biodiversity as well as regulation of carbon cycling and climate. There are about 117 million lakes worldwide and a high need for regular monitoring of their water quality. European Union Water Framework Directive (WFD) stipulates that member states shall establish a programme for monitoring the ecological status of all water bodies larger than 50 ha, in order to ensure future quality and quantity of inland waters. But only a fraction of lakes is included in in-situ monitoring networks due to limited resources. In Latvia, there are 2256 lakes larger than 1 ha covering 1.5% of Latvian territory, and approximately 300 lakes are larger than 50 ha, but only 180 are included in Inland water monitoring program, in addition, most of them are monitored once in three to six years. Besides, local municipalities are responsible for the management of lakes, and they are also interested in the assessment of ecological status and regular monitoring of these valuable assets. </p><p>Satellite data is a feasible way to monitor lakes over a large region with reasonable frequency and support the WFD status assessment process. There are several satellite-based sensors (eg. MERIS, MODIS, OLCI) available specially designed for monitoring of water quality parameters, however, they are limited only to use for large water bodies due to a coarse spatial resolution (250...1000 m/pix). Sentinel-2 MSI is a space-borne instrument providing 10...20 m/pix multispectral data on a regular basis (every 5 days at the equator and 2..3 days in Latvia), thus making it attractive for monitoring of inland water bodies, especially the small ones (<1 km<sup>2</sup>). </p><p>Development of Sentinel-2 satellite data-based service (SentiLake) for monitoring of Latvian lakes is being implemented within the ESA PECS for Latvia program. The pilot territory covers two regions in Latvia and includes more than 100 lakes larger than 50 ha. Automated workflow for selecting and processing of available Sentinel-2 data scenes for extracting of water quality parameters (chlorophyll-a and TSM concentrations) for each target water body has been developed. Latvia is a northern country with a frequently cloudy sky, therefore, optical remote sensing is challenging in or region. However, our results show that 1...4 low cloud cover Sentinel-2 data acquisitions per month could be expected due to high revisit frequency of Sentinel-2 satellites. Combination of C2X and C2RCC processors was chosen for the assessment of chl-a concentration showing the satisfactory performance - R<sup>2</sup> = 0,82 and RMSE = 21,2 µg/l. Chl-a assessment result is further converted and presented as a lake quality class. It is expected that SentiLake will provide supplementary data to limited in situ data for filling gaps and retrospective studies, as well as a visual tool for communication with the target audience.</p>

scholarly journals Chlorophyll and Suspended Solids Estimation in Portuguese Reservoirs (Aguieira and Alqueva) from Sentinel-2 Imagery

Water ◽  
2021 ◽  
Vol 13 (18) ◽  
pp. 2479
Author(s):  
Vítor Hugo Neves ◽  
Giorgio Pace ◽  
Jesús Delegido ◽  
Sara C. Antunes
Keyword(s):  
Water Quality ◽  
Satellite Data ◽  
Suspended Solids ◽  
Low Cost ◽  
Water Quality Assessment ◽  
Fine Tuning ◽  
Future Research ◽  
Chl A ◽  
Sentinel 2

Reservoirs have been subject to anthropogenic stressors, becoming increasingly degraded. The evaluation of ecological potential in reservoirs is remarkably challenging, and consistent and regular monitoring using the traditional in situ methods defined in the WFD is often time- and money-consuming. Alternatively, remote sensing offers a low-cost, high frequency, and practical complement to these methods. This paper proposes a novel approach, using a C2RCC processor to analyze Sentinel-2 imagery data to retrieve information on water quality in two reservoirs of Portugal, Aguieira and Alqueva. We evaluate the temporal and spatial evolution of Chl a and total suspended solids (TSS), between 2018 and 2020, comparing in situ and satellite data. Generally, Alqueva reservoir allowed lower relative (NRMSE = 8.9% for Chl a and NRMSE = 21.9% for TSS) and systematic (NMBE = 1.7% for Chl a and NMBE = 2.0% for TSS) errors than Aguieira, where some fine-tuning would be required. Our paper shows how satellite data can be fundamental for water-quality assessment to support the effective and sustainable management of inland waters. In addition, it proposes solutions for future research in order to improve upon the methods used and solve the challenges faced in this study.

Classification Model for Water Quality using Machine Learning Techniques

2015 ◽  
Vol 9 (6) ◽  
pp. 45-52 ◽  
Author(s):  
Salisu Yusuf Muhammad ◽  
Mokhairi Makhtar ◽  
Azilawati Rozaimee ◽  
Azwa Abdul Aziz ◽  
Azrul Amri Jamal
Keyword(s):  
Machine Learning ◽  
Water Quality ◽  
Classification Model ◽  
Machine Learning Techniques ◽  
Learning Techniques
Sign in / Sign up

Export Citation Format

Share Document