scholarly journals Prediction of Algal Chlorophyll-a and Water Clarity in Monsoon-Region Reservoir Using Machine Learning Approaches

Water ◽  
2019 ◽  
Vol 12 (1) ◽  
pp. 30 ◽  
Author(s):  
Md Mamun ◽  
Jung-Jae Kim ◽  
Md Ashad Alam ◽  
Kwang-Guk An
Keyword(s):  
Chlorophyll A ◽  
Trophic State ◽  
Secchi Depth ◽  
Water Clarity ◽  
Coefficient Of Determination ◽  
Annual Rainfall ◽  
Support Vector ◽  
Chl A ◽  
Svm Model ◽  
Ann Models

The prediction of algal chlorophyll-a and water clarity in lentic ecosystems is a hot issue due to rapid deteriorations of drinking water quality and eutrophication processes. Our key objectives of the study were to predict long-term algal chlorophyll-a and transparency (water clarity), measured as Secchi depth, in spatially heterogeneous and temporally dynamic reservoirs largely influenced by the Asian monsoon during 2000–2017 and then determine the reservoir trophic state using a multiple linear regression (MLR), support vector machine (SVM) and artificial neural network (ANN). We tested the models to analyze the spatial patterns of the riverine zone (Rz), transitional zone (Tz) and lacustrine zone (Lz) and temporal variations of premonsoon, monsoon and postmonsoon. Monthly physicochemical parameters and precipitation data (2000–2017) were used to build up the models of MLR, SVM and ANN and then were confirmed by cross-validation processes. The model of SVM showed better predictive performance than the models of MLR and ANN, in both before validation and after validation. Values of root mean square error (RMSE) and mean absolute error (MAE) were lower in the SVM model, compared to the models of MLR and ANN, indicating that the SVM model has better performance than the MLR and ANN models. The coefficient of determination was higher in the SVM model, compared to the MLR and ANN models. The mean and maximum total suspended solids (TSS), nutrients (total nitrogen (TN) and total phosphorus (TP)), water temperature (WT), conductivity and algal chlorophyll (CHL-a) were in higher concentrations in the riverine zone compared to transitional and lacustrine zone due to surface run-off from the watershed. During the premonsoon and postmonsoon, the average annual rainfall was 59.50 mm and 54.73 mm whereas it was 236.66 mm during the monsoon period. From 2013 to 2017, the trophic state of the reservoir on the basis of CHL-a and SD was from mesotrophic to oligotrophic. Analysis of the importance of input variables indicated that WT, TP, TSS, TN, NP ratios and the rainfall influenced the chlorophyll-a and transparency directly in the reservoir. These findings of the algal chlorophyll-a predictions and Secchi depth may provide key clues for better management strategy in the reservoir.

scholarly journals Machine Learning-Based Prediction of Chlorophyll-a Variations in Receiving Reservoir of World’s Largest Water Transfer Project—A Case Study in the Miyun Reservoir, North China

Water ◽  
2021 ◽  
Vol 13 (17) ◽  
pp. 2406
Author(s):  
Zhenmei Liao ◽  
Nan Zang ◽  
Xuan Wang ◽  
Chunhui Li ◽  
Qiang Liu
Keyword(s):  
Machine Learning ◽  
Water Quality ◽  
Chlorophyll A ◽  
Trophic State ◽  
Water Transfer ◽  
Support Vector ◽  
Miyun Reservoir ◽  
Chl A ◽  
Svm Model

Although water transfer projects can alleviate the water crisis, they may cause potential risks to water quality safety in receiving areas. The Miyun Reservoir in northern China, one of the receiving reservoirs of the world’s largest water transfer project (South-to-North Water Transfer Project, SNWTP), was selected as a case study. Considering its potential eutrophication trend, two machine learning models, i.e., the support vector machine (SVM) model and the random forest (RF) model, were built to investigate the trophic state by predicting the variations of chlorophyll-a (Chl-a) concentrations, the typical reflection of eutrophication, in the reservoir after the implementation of SNWTP. The results showed that compared with the SVM model, the RF model had higher prediction accuracy and more robust prediction ability with abnormal data, and was thus more suitable for predicting Chl-a concentration variations in the receiving reservoir. Additionally, short-term water transfer would not cause significant variations of Chl-a concentrations. After the project implementation, the impact of transferred water on the water quality of the receiving reservoir would have gradually increased. After a 10-year implementation, transferred water would cause a significant decline in the receiving reservoir’s water quality, and Chl-a concentrations would increase, especially from July to August. This led to a potential risk of trophic state change in the Miyun Reservoir and required further attention from managers. This study can provide prediction techniques and advice on water quality security management associated with eutrophication risks resulting from water transfer projects.

APLIKASI CITRA LANDSAT 8 OLI UNTUK IDENTIFIKASI STATUS TROFIK WADUK GAJAH MUNGKUR WONOGIRI, JAWA TENGAH

2017 ◽  
Vol 19 (2) ◽  
pp. 113
Author(s):  
Kusuma Wardani Laksitaningrum ◽  
Wirastuti Widyatmanti
Keyword(s):  
Chlorophyll A ◽  
Total Phosphorus ◽  
Trophic State ◽  
Water Clarity ◽  
Coefficient Of Determination ◽  
Physical Factors ◽  
Landsat 8 ◽  
Trophic State Index ◽  
Landsat 8 Oli ◽  
State Index

<p align="center"><strong>ABSTRAK</strong></p><p class="abstrak">Waduk Gajah Mungkur (WGM) adalah bendungan buatan yang memiliki luas genangan maksimum 8800 ha, terletak di Desa Pokoh Kidul, Kecamatan Wonogiri, Kabupaten Wonogiri. Kondisi perairan WGM dipengaruhi oleh faktor klimatologis, fisik, dan aktivitas manusia yang dapat menyumbang nutrisi sehingga mempengaruhi status trofiknya. Tujuan dari penelitian ini adalah mengkaji kemampuan citra Landsat 8 OLI untuk memperoleh parameter-parameter yang digunakan untuk menilai status trofik, menentukan dan memetakan status trofik yang diperoleh dari citra Landsat 8 OLI, dan mengevaluasi hasil pemetaan dan manfaat citra penginderaan jauh untuk identifikasi status trofik WGM. Identifikasi status trofik dilakukan berdasarkan metode <em>Trophic State Index</em> (TSI) Carlson (1997) menggunakan tiga parameter yaitu kejernihan air, total fosfor, dan klorofil-a. Model yang diperoleh berdasar pada rumus empiris dari hasil uji regresi antara pengukuran di lapangan dan nilai piksel di citra Landsat 8 OLI. Model dipilih berdasarkan nilai koefisien determinasi (R<sup>2</sup>) tertinggi. Hasil penelitian merepresentasikan bahwa nilai R<sup>2</sup> kejernihan air sebesar 0,813, total fosfor sebesar 0,268, dan klorofil-a sebesar 0,584. Apabila nilai R<sup>2 </sup>mendekati 1, maka semakin baik model regresi dapat menjelaskan suatu parameter status trofik. Berdasarkan hasil kalkulasi diperoleh distribusi yang terdiri dari kelas eutrofik ringan, eutrofik sedang, dan eutrofik berat yaitu pada rentang nilai indeks 50,051 – 80,180. Distribusi terbesar adalah eutrofik sedang. Hal tersebut menunjukkan tingkat kesuburan perairan yang tinggi dan dapat membahayakan makhluk hidup lain.</p><p><strong>Kata kunci: </strong>Waduk Gajah Mungkur, citra Landsat 8 OLI, regresi, TSI, status trofik</p><p class="judulABS"><strong>ABSTRACT</strong></p><p class="Abstrakeng">Gajah Mungkur Reservoir is an artificial dam that has a maximum inundated areas of 8800 ha, located in Pokoh Kidul Village, Wonogiri Regency. The reservoir’s water conditions are affected by climatological and physical factors, as well as human activities that can contribute to nutrients that affect its trophic state. This study aimed to assess the Landsat 8 OLI capabilities to obtain parameters that are used to determine its trophic state, identifying and mapping the trophic state based on parameters derived from Landsat 8 OLI, and evaluating the results of the mapping and the benefits of remote sensing imagery for identification of its trophic state. Identification of trophic state is based on Trophic State Index (TSI) Carlson (1997), which uses three parameters there are water clarity, total phosphorus, and chlorophyll-a. The model is based on an empirical formula of regression between measurements in the field and the pixel values in Landsat 8 OLI. Model is selected on the highest value towards coefficient of determination (R<sup>2</sup>). The results represented that R<sup>2</sup> of water clarity is 0.813, total phosphorus is 0.268, and chlorophyll-a is 0.584. If R<sup>2</sup> close to 1, regression model will describe the parameters of the trophic state better. Based on the calculation the distribution consists of mild eutrophic, moderate eutrophic, and heavy eutrophic that has index values from 50.051 to 80.18. The most distribution is moderate eutrophication, and it showed the high level of trophic state and may harm other living beings.</p><p><strong><em>Keywords: </em></strong><em>Gajah Mungkur Reservoir, </em><em>L</em><em>andsat 8 OLI satellite imagery, regression, TSI, trophic state</em></p>

scholarly journals Correlation between the structure and skin permeability of compounds

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ruolan Zeng ◽  
Jiyong Deng ◽  
Limin Dang ◽  
Xinliang Yu
Keyword(s):  
Large Data ◽  
Qsar Model ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Skin Permeability ◽  
Data Set ◽  
Test Set ◽  
Svm Algorithm ◽  
Svm Model ◽  
Toxicity Relationship

AbstractA three-descriptor quantitative structure–activity/toxicity relationship (QSAR/QSTR) model was developed for the skin permeability of a sufficiently large data set consisting of 274 compounds, by applying support vector machine (SVM) together with genetic algorithm. The optimal SVM model possesses the coefficient of determination R2 of 0.946 and root mean square (rms) error of 0.253 for the training set of 139 compounds; and a R2 of 0.872 and rms of 0.302 for the test set of 135 compounds. Compared with other models reported in the literature, our SVM model shows better statistical performance in a model that deals with more samples in the test set. Therefore, applying a SVM algorithm to develop a nonlinear QSAR model for skin permeability was achieved.

scholarly journals Color, chlorophyll a , and suspended solids effects on Secchi depth in lakes: implications for trophic state assessment

2019 ◽  
Vol 29 (3) ◽  
Author(s):  
Patrick L. Brezonik ◽  
R. William Bouchard ◽  
Jacques C. Finlay ◽  
Claire G. Griffin ◽  
Leif G. Olmanson ◽  
...  
Keyword(s):  
Chlorophyll A ◽  
Trophic State ◽  
Suspended Solids ◽  
Secchi Depth ◽  
State Assessment

Prediction of side weir discharge coefficient by support vector machine technique

2016 ◽  
Vol 16 (4) ◽  
pp. 1002-1016 ◽  
Author(s):  
Hazi Mohammad Azamathulla ◽  
Amir Hamzeh Haghiabi ◽  
Abbas Parsaie
Keyword(s):  
Support Vector Machine ◽  
Discharge Coefficient ◽  
Sensitivity Analyses ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Good Prediction ◽  
Effective Parameters ◽  
Side Weir ◽  
Svm Model ◽  
Soft Computing Techniques

Side weirs have many possible applications in the field of hydraulic engineering. They are also considered an important structure in hydro systems. In this study, the support vector machine (SVM) technique was employed to predict the side weir discharge coefficient. The performance of SVM was compared with other types of soft computing techniques such as artificial neural networks (ANN) and adaptive neuro fuzzy inference systems (ANFIS). While ANN and ANFIS models provided a good prediction performance, the SVM model with a radial basis function kernel function outperforms them. The best SVM model was developed with a gamma coefficient and epsilon of 15 and 0.3, respectively. The SVM yielded a coefficient of determination (R2) equal to 0.96 and 0.93 for the training and testing data. Sensitivity analyses of the ANN, ANFIS and SVM models showed that the Froude number and ratio of weir length to the flow depth upstream of the weir are the most effective parameters for the prediction of the discharge coefficient.

scholarly journals ASSESSMENT OF SEAGRASS PERCENT COVER AND WATER QUALITY USING UAV IMAGES AND FIELD MEASUREMENTS IN BOLINAO, PANGASINAN

2019 ◽  
Vol XLII-4/W19 ◽  
pp. 233-240
Author(s):  
M. K. M. R. Guerrero ◽  
J. A. M. Vivar ◽  
R. V. Ramos ◽  
A. M. Tamondong
Keyword(s):  
Water Quality ◽  
Regression Analysis ◽  
Chlorophyll A ◽  
Quality Parameters ◽  
Water Quality Parameters ◽  
Support Vector ◽  
Percent Cover ◽  
Chl A ◽  
Relationship Of ◽  
The Relationship

Abstract. The sensitivity to changes in water quality inherent to seagrass communities makes them vital for determining the overall health of the coastal ecosystem. Numerous efforts including community-based coastal resource management, conservation and rehabilitation plans are currently undertaken to protect these marine species. In this study, the relationship of water quality parameters, specifically chlorophyll-a (chl-a) and turbidity, with seagrass percent cover is assessed quantitatively. Support Vector Machine, a pixel-based image classification method, is applied to determine seagrass and non-seagrass areas from the orthomosaic which yielded a 91.0369% accuracy. In-situ measurements of chl-a and turbidity are acquired using an infinity-CLW water quality sensor. Geostatistical techniques are utilized in this study to determine accurate surfaces for chl-a and turbidity. In two hundred interpolation tests for both chl-a and turbidity, Simple Kriging (Gaussian-model type and Smooth- neighborhood type) performs best with Mean Prediction equal to −0.1371 FTU and 0.0061 μg/L, Root Mean Square Standardized error equal to −0.0688 FTU and −0.0048 μg/L, RMS error of 8.7699 FTU and 1.8006 μg/L and Average Standard Error equal to 10.8360 FTU and 1.6726 μg/L. Zones are determined using fishnet tool and Moran’s I to calculate for the seagrass percent cover. Ordinary Least Squares (OLS) is used as a regression analysis to quantify the relationship of seagrass percent cover and water quality parameters. The regression analysis result indicates that turbidity has an inverse relationship while chlorophyll-a has a direct relationship with seagrass percent cover.

scholarly journals Estimation of Leaf Chlorophyll a, b and Carotenoid Contents and Their Ratios Using Hyperspectral Reflectance

2020 ◽  
Vol 12 (19) ◽  
pp. 3265
Author(s):  
Rei Sonobe ◽  
Hiroto Yamashita ◽  
Harumi Mihara ◽  
Akio Morita ◽  
Takashi Ikka
Keyword(s):  
Chlorophyll A ◽  
High Performance ◽  
Machine Learning Algorithms ◽  
Ion Concentration ◽  
Gradient Boosting ◽  
Support Vector ◽  
Culture Methods ◽  
Chl A ◽  
Stochastic Gradient Boosting ◽  
Processing Techniques

Japanese horseradish (wasabi) grows in very specific conditions, and recent environmental climate changes have damaged wasabi production. In addition, the optimal culture methods are not well known, and it is becoming increasingly difficult for incipient farmers to cultivate it. Chlorophyll a, b and carotenoid contents, as well as their allocation, could be an adequate indicator in evaluating its production and environmental stress; thus, developing an in situ method to monitor photosynthetic pigments based on reflectance could be useful for agricultural management. Besides original reflectance (OR), five pre-processing techniques, namely, first derivative reflectance (FDR), continuum-removed (CR), de-trending (DT), multiplicative scatter correction (MSC), and standard normal variate transformation (SNV), were compared to assess the accuracy of the estimation. Furthermore, five machine learning algorithms—random forest (RF), support vector machine (SVM), kernel-based extreme learning machine (KELM), Cubist, and Stochastic Gradient Boosting (SGB)—were considered. To classify the samples under different pH or sulphur ion concentration conditions, the end of the red edge bands was effective for OR, FDR, DT, MSC, and SNV, while a green-peak band was effective for CR. Overall, KELM and Cubist showed high performance and incorporating pre-processing techniques was effective for obtaining estimated values with high accuracy. The best combinations were found to be DT–KELM for chl a (RPD = 1.511–5.17, RMSE = 1.23–3.62 μg cm−2) and chl a:b (RPD = 0.73–3.17, RMSE = 0.13–0.60); CR–KELM for chl b (RPD = 1.92–5.06, RMSE = 0.41–1.03 μg cm−2) and chl a:car (RPD = 1.31–3.23, RMSE = 0.26–0.50); SNV–Cubist for car (RPD = 1.63–3.32, RMSE = 0.31–1.89 μg cm−2); and DT–Cubist for chl:car (RPD = 1.53–3.96, RMSE = 0.27–0.74).

scholarly journals Eutrophication Factor Analysis Using Carlson Trophic State Index (CTSI) Towards Non-Algal Impact Reservoirs in Taiwan

2021 ◽  
Author(s):  
Jr-Lin Lin ◽  
Arthur Karangan ◽  
Ying Min Huang ◽  
Shyh-Fang Kang
Keyword(s):  
Drinking Water ◽  
Influencing Factors ◽  
Trophic State ◽  
Secchi Depth ◽  
Growth Potential ◽  
Trophic State Index ◽  
Water Reservoirs ◽  
Chl A ◽  
Eutrophication Potential ◽  
State Index

Abstract Carlson trophic state index (CTSI) has been commonly adopted to assess the eutrophication potential of reservoirs or lakes in water quality management. This study aims to analyze the influencing factors of CTSI-based eutrophication by using Pearson correlation analysis and principal component analysis (PCA) with long-term data from 2008 to 2019 on 21 drinking water reservoirs in Taiwan. The trophic state index (TSI) deviation indicates that most drinking water reservoirs in Taiwan, around 45.5% of statistical data fall into non-algal turbidity with surplus phosphorus, especially in the spring and winter season. Besides, there are about 78 % of total collected data show that TSI (Chl-a) is less than TSI (SD) due to the small particulate predominance. On the other hand, three TSI variables (Secchi depth (SD), total phosphorus (TP) and chlorophyll-a (Chl-a)) of CTSI exhibits insignificant correlation to each other in most cases. At such a condition, the probability of eutrophication (TSI>50) based on TSI (SD) is 63%, while it is only as low as 20% based on TSI (TP) and TSI (Chl-a). The influencing factors of eutrophication variables by suspended solids (SS) composition and turbidity have shown that the SD is strongly influenced by non-algal SS. The deviations of three TSI have shown that the highest algae-induced eutrophication potential occurs in the summer season. In addition, the TP is the most significant loading factor of algae-induced eutrophication for drinking water reservoirs. It is concluded that the CTSI has limited applicability to identify the trophic status of drinking water reservoirs in Taiwan in the presence of sustainable non-algal turbidity comparative Chl-a that completely represents algal growth potential (AGP).

scholarly journals Assessment of Water Quality Based on Trophic Status and Nutrients-Chlorophyll Empirical Models of Different Elevation Reservoirs

Water ◽  
2021 ◽  
Vol 13 (24) ◽  
pp. 3640
Author(s):  
Md Mamun ◽  
Usman Atique ◽  
Kwang-Guk An
Keyword(s):  
Water Quality ◽  
Trophic State ◽  
Trophic Status ◽  
Water Clarity ◽  
Empirical Models ◽  
Cyanobacterial Blooms ◽  
Anthropogenic Factors ◽  
Trophic State Index ◽  
Chl A ◽  
State Index

Water quality degradation is one of the most pressing environmental challenges in reservoirs around the world and makes the trophic status assessment of reservoirs essential for their restoration and sustainable use. The main aims of this study were to determine the spatial variations in water quality and trophic state of 204 South Korean reservoirs at different altitude levels. The results demonstrated mean total phosphorus (TP), chlorophyll-a (CHL-a), total suspended solids (TSS), organic matter indicators (chemical oxygen demand: COD; total organic carbon: TOC), water temperature (WT), and electrical conductivity (EC) remain consistently higher in the very lowland reservoirs (VLLR) than those in other altitudes, due to sedimentary or alluvial watersheds. The average TP and CHL-a levels in VLLR crossed the limit of the eutrophic water, symptomizing a moderate risk of cyanobacterial blooms. Empirical models were developed to identify critical variables controlling algal biomass and water clarity in reservoirs. The empirical analyses of all reservoir categories illustrated TP as a better predictor of CHL-a (R2 = 0.44, p < 0.01) than TN (R2 = 0.02, p < 0.05) as well as showed strong P-limitation based on TN:TP ratios. The algal productivity of VLLR (R2 = 0.61, p < 0.01) was limited by phosphorus, while highland reservoirs (HLR) were phosphorus (R2 = 0.23, p < 0.03) and light-limited (R2 = 0.31, p < 0.01). However, TSS showed a highly significant influence on water clarity compared to TP and algal CHL-a in all reservoirs. TP and TSS explained 47% and 34% of the variance in non-algal turbidity (NAT) in HLR. In contrast, the TP and TSS variances were 18% and 29% in midland reservoirs (MLR) and 32% and 20% in LLR. The trophic state index (TSI) of selected reservoirs varied between mesotrophic to eutrophic states as per TSI (TP), TSI (CHL-a), and TSI (SD). Mean TSI (CHL-a) indicated all reservoirs as eutrophic. Trophic state index deviation (TSID) assessment also complemented the phosphorus limitation characterized by the blue-green algae (BGA) domination in all reservoirs. Overall, reservoirs at varying altitudes reflect the multiplying impacts of anthropogenic factors on water quality, which can provide valuable insights into reservoir water quality management.

A Statistical Machine Learning Model to Predict Equivalent Circulation Density ECD while Drilling, Based on Principal Components Analysis PCA

2021 ◽  
Author(s):  
Ahmed AlSaihati ◽  
Salaheldin Elkatatny ◽  
Hani Gamal ◽  
Abdulazeez Abdulraheem
Keyword(s):  
Machine Learning ◽  
Principal Components Analysis ◽  
Principal Components ◽  
Regularization Parameter ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Linear Kernel ◽  
Svm Model ◽  
Components Analysis ◽  
Testing Set

Abstract Mathematical equations, based on conservation of mass and momentum, are used to determine the ECD at different depths in the wellbore. However, such equations do not consider important factors that have a influence on the ECD such as: (i) bottom hole temperature, (ii) pipe rotation and eccentricity, and (iii) wellbore roughness. Thus, discrepancy between the calculated ECDs and actual ones has been reported in the literature. This paper aims to explore how artificial intelligence (AI) and machine learning (ML) could provide real-time accurate prediction of the ECD, to have more insight and management of wellbore downhole conditions. For this purpose, a supervised ML algorithm, support vector machine (SVM), based on principal components analysis (PCA), was developed. Actual field data of Well-1 including drilling surface parameters and ECDs, measured by downhole sensors, were collected to develop a classical SVM model. The dataset was split with an 80/20 training-testing data ratio. Sensitivity analysis with different SVM parameters such as regularization parameter C, gamma, kernel type (linear, radial basis function "RBF") was performed. The performance of the model was assessed in terms of root mean square error (RMSE) and coefficient of determination (R2). Afterward, PCA was applied to the dataset of Well-1 to develop an SVM model using the transformed dataset in PCA space. The performance of the model while using different numbers of principal components was evaluated. The results showed that the classical SVM with the linear kernel predicted the ECD with RMSE of 0.53 and R2 of 0.97 in the training set, while RMSE and R2 were 0.56 and 0.97 respectively in the testing set. The PCA-based SVM model, with the linear kernel and four principal components (93.53% variation of the dataset), predicted the ECD with RMSE 0.79 and R2 of 0.95 in the testing set.

Sign in / Sign up

Export Citation Format

Share Document