Evaluating the accuracy of ANN and LR models to estimate the water quality in Zarivar International Wetland, Iran

Amanollahi, Jamil; Kaboodvandpour, Shahram; Majidi, Hiva

doi:10.1007/s11069-016-2641-1

Cited by 25 publications

(13 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The results achieved for both TSS and chlorophyll-a predictions reached a higher R 2 coefficient than research studies for the same region [20,27,48], as well as other similar studies over different areas [1,26]. Since the two studied regions present different environmental characteristics, these results indicated the soundness of the proposed method for water quality monitoring through remote sensing and ML techniques.…”

Section: Discussionsupporting

confidence: 65%

“…The red channel was excluded because there are several low-cost sensors (cameras) available on the market, used in UAVs, that are modified to present the NIR channel in place of the red band. Besides that, the B, G, and NIR bands are widely used for similar applications involving chlorophyll-a [6,26] and TSS [11,26,27] prediction in water bodies. For Sentinel-2, we considered Bands 2 (Blue, 0.490 µm), 3 (Green, 0.560 µm), and 8 (NIR, 0.842 µm), which have similar bandwidths to the sensors used in the UAV.…”

Section: Remote Sensingmentioning

confidence: 99%

See 1 more Smart Citation

A Method for Chlorophyll-a and Suspended Solids Prediction through Remote Sensing and Machine Learning

Kupssinskü

Guimarães

Souza

et al. 2020

Sensors

View full text Add to dashboard Cite

† This paper is an extended version of our paper published in Kupssinskü, L.; Guimarães, T.; Freitas, R.; de Souza, E.; Rossa, P.; Ademir Marques, J.; Veronez, M.; Junior, L.G.; Mauad, F.; Cazarin, C. Prediction of chlorophyll-a and suspended solids through remote sensing and artificial neural networks.Abstract: Total Suspended Solids (TSS) and chlorophyll-a concentration are two critical parameters to monitor water quality. Since directly collecting samples for laboratory analysis can be expensive, this paper presents a methodology to estimate this information through remote sensing and Machine Learning (ML) techniques. TSS and chlorophyll-a are optically active components, therefore enabling measurement by remote sensing. Two study cases in distinct water bodies are performed, and those cases use different spatial resolution data from Sentinel-2 spectral images and unmanned aerial vehicles together with laboratory analysis data. In consonance with the methodology, supervised ML algorithms are trained to predict the concentration of TSS and chlorophyll-a. The predictions are evaluated separately in both study areas, where both TSS and chlorophyll-a models achieved R-squared values above 0.8.Sensors 2020, 20, 2125 2 of 18 bodies [3]. Moreover, the suspended solids may indicate erosive processes within the watershed and additional water pollution since it can carry or store pollutants [4].Generally, once the samples get to a laboratory, their concentrations are analyzed, and manual measurements are taken to extract these parameters. The involved processes are costly, time-consuming, and require skilled personnel [5]. Although there are accurate evaluations, they do not indicate the individual spatio-temporal variation of water quality [6].In this sense, applications involving remote sensing can overcome the drawbacks of conventional monitoring since they allow real-time, spatial, continuous, and long-term monitoring in large areas [7,8]. The presence of components alters the spectral characteristics of the pure water, called Optically Active Components (OAC). The main OACs in water bodies are chlorophyll, suspended solids, and organic material [4]. The possibility of monitoring non-accessible areas and composing time series of water quality from historical data of remote sensing [9] are also factors that make this tool essential and its use promising.Among the most common satellites in OAC remote sensing studies are Landsat 8 and Sentinel-2. Although Landsat is more widely used, the European Sentinel-2 satellite has promising characteristics: it has higher spatial resolution than Landsat 8 and also spectral bands in the region called the red edge, which is of great interest for water and vegetation studies.Remote sensing serves as a powerful technique for monitoring environmental and seasonal changes, and its ability to remotely monitor water resources has increased in recent decades because of the quality and availability of satellite imagery data [10]. Even so, the analysis of small water bodies may not be adequ...

show abstract

Section: Discussionsupporting

confidence: 65%

Section: Remote Sensingmentioning

confidence: 99%

A Method for Chlorophyll-a and Suspended Solids Prediction through Remote Sensing and Machine Learning

Kupssinskü

Guimarães

Souza

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…Some empirical methods have used dominant wavelengths that obtain poor accuracy, where the R 2 value is less than 0.7 on average [10,11,27]. Compared with some hyperbolic equations in describing the biological processes in wetlands, the traditional prediction method for the numerical values of COD is produced through linear regression [13,17]. Phuong et al predicted BOD and COD removals through a traditional ANN method, using either COD or BOD as input in ANN to predict the other one [25], which was cost-inefficient and time-consuming.…”

Section: Discussionmentioning

confidence: 99%

Mapping Water Quality Parameters in Urban Rivers from Hyperspectral Images Using a New Self-Adapting Selection of Multiple Artificial Neural Networks

Zhang

Ren

et al. 2020

Remote Sensing

View full text Add to dashboard Cite

Protection of water environments is an important part of overall environmental protection; hence, many people devote their efforts to monitoring and improving water quality. In this study, a self-adapting selection method of multiple artificial neural networks (ANNs) using hyperspectral remote sensing and ground-measured water quality data is proposed to quantitatively predict water quality parameters, including phosphorus, nitrogen, biochemical oxygen demand (BOD), chemical oxygen demand (COD), and chlorophyll a. Seventy-nine ground measured data samples are used as training data in the establishment of the proposed model, and 30 samples are used as testing data. The proposed method based on traditional ANNs of numerical prediction involves feature selection of bands, self-adapting selection based on multiple selection criteria, stepwise backtracking, and combined weighted correlation. Water quality parameters are estimated with coefficient of determination R 2 ranging from 0.93 (phosphorus) to 0.98 (nitrogen), which is higher than the value (0.7 to 0.8) obtained by traditional ANNs. MPAE (mean percent of absolute error) values ranging from 5% to 11% are used rather than root mean square error to evaluate the predicting precision of the proposed model because the magnitude of each water quality parameter considerably differs, thereby providing reasonable and interpretable results. Compared with other ANNs with backpropagation, this study proposes an auto-adapting method assisted by the above-mentioned methods to select the best model with all settings, such as the number of hidden layers, number of neurons in each hidden layer, choice of optimizer, and activation function. Different settings for ANNS with backpropagation are important to improve precision and compatibility for different data. Furthermore, the proposed method is applied to hyperspectral remote sensing images collected using an unmanned aerial vehicle for monitoring the water quality in the Shiqi River, Zhongshan City, Guangdong Province, China. Obtained results indicate the locations of pollution sources.

show abstract

“…Estudos conduzidos por diversos pesquisadores com base em dados obtidos coletas de campo, laboratório e obtidos por sensoriamento remoto analisaram os efeitos de diferentes concentrações dos COAs na resposta espectral de corpos d'água e propõem modelos que visam estimativas de concentração dos mesmos presentes na água, através de razões de bandas (RUNDQUIST et al, 1996;GITELSON, 2006;GITELSON et al, 2007;LE et al, 2009;NOVO et al, 2013;GUO et al, 2016;AMANOLLAHI;KABOODVANDPOUR;MAJIDI, 2017), sejam elas simples, com apenas duas feições, ou mais complexas (LONDE, 2008;RUDORFF, 2006;GOODIN et al, 1993;CHENG et al, 2013;GUO et al, 2016; AMANOLLAHI; KABOODVANDPOUR; MAJIDI, 2017).…”

Section: Estudos Desenvolvidosunclassified

“…Sobre estas limitações nos estudos que visam monitorar as qualidades da água usando diferentes sensores e modelos, Amanollahi, Kabbodvandpour e Majidi (2017) destacam que a baixa qualidade de dados (relação sinal-ruído) e baixa quantificação radiométrica (inferior 12 bits) nos sensores utilizados podem ser um dos motivos para tal. Diversos autores(WATANABE et al, 2015;HA et al, 2017;AMANOLLAHI; KABOODVANDPOUR; MAJIDI, 2017) apontam que o novo sensor OLI (Operational Land Imager), a bordo do satélite Landsat 8, por apresentar alta qualidade de dados (relação sinalruído) e quantificação radiométrica (12 bits), poderia melhorar os resultados estimados de diferentes propriedades químicas e físicas da água.Em relação a utilização dos satélites Landsat para estudos de corpos d'água, Montanher, Barbosa e Novo (2013) apontam que, ao contrário dos dados de satélites como o MERIS, por exemplo, que é um sensor cujas características são adequadas aos sistemas aquáticos, os sensores da série de satélites Landsat foram desenvolvidos para aplicações relacionadas ao estudo de sistemas terrestres. No entanto, Ha et al (2017) afirmam que, embora os sensores da série Landsat não tenham sido projetados para a aplicação da qualidade da água, desde seus estágios iniciais as imagens Landsat foram extensivamente aplicadas a isso através da estimativa das concentrações de clorofila-a e fitoplâncton e o monitoramento de florações de algas e macrófitas.…”

unclassified

Utilização de imagens de satélite para predição de clorofila-a e sólidos suspensos em corpos d\'água: estudo de caso da Represa do Lobo/SP

Guimarães¹

View full text Add to dashboard Cite

A concretização deste trabalho seria impossível se eu não contasse com o apoio de diversas pessoas, que de diferentes formas estiveram presentes e influenciaram minha caminhada até aqui. Agradeço ao professor Frederico Fábio Mauad pela oportunidade, orientação e por garantir toda a infraestrutura necessária para o desenvolvimento deste trabalho. Não poderia também deixar de agradecer o técnico do Núcleo de Hidrometria, Miro, pela paciência e auxílio nas coletas de campo, além das inúmeras histórias e experiências compartilhadas. Aos meus colegas do Núcleo de Hidrometria, destacando os que ingressaram comigo no programa: Allita, pelo apoio em diversos momentos, sejam eles bons ou ruins; Gabriela e Mariana, pela amizade, abraços e carinho compartilhados; e Phelipe, pela companhia e parceria em diversos momentos. Em especial agradeço à Gabriela Leite Neves por todo o auxílio durante as incansáveis análises realizadas e também pelas conversas e risadas compartilhadas durante este período que com certeza fizeram com que tudo fluísse de uma forma muito mais leve, e ao Carlos Martinez, por ter me apresentado ao Matlab e à ferramenta de redes neurais, o que realmente fez toda a diferença neste trabalho. Ao professor Maurício Veronez, da UNISINOS/RS, pelo auxílio em diversas etapas do desenvolvimento deste trabalho, sempre me mantendo confiante de que daria tudo certo. Aos meus amigos do sul, amigos de longa data (Ludmila), da escola (Bruna) e a da faculdade (Gabriela, Tatiana, Rosele e Emilie), por respeitarem minha ausência neste tempo e me incentivarem sempre. E, por fim, meu agradecimento especial, sincero e eterno a minha família (mãe Leila, pai Renato e irmãs Terena e Naiara) e ao meu namorado (Guilherme) pelo apoio, carinho e amor que sempre me dedicaram, por terem respeitado minha escolha de sair de casa e ir para outro estado fazer mestrado e ainda terem me incentivado a enfrentar todas as dificuldades que surgiram. Se eu cheguei até aqui, com certeza foi porque vocês foram meus pilares, amo vocês! RESUMO GUIMARÃES, T. T. Utilização de imagens de satélite para predição de clorofila-a e sólidos suspensos em corpos d'água: estudo de caso da Represa do Lobo/SP. 2019. 113f.

show abstract

Evaluating the accuracy of ANN and LR models to estimate the water quality in Zarivar International Wetland, Iran

Cited by 25 publications

References 66 publications

A Method for Chlorophyll-a and Suspended Solids Prediction through Remote Sensing and Machine Learning

A Method for Chlorophyll-a and Suspended Solids Prediction through Remote Sensing and Machine Learning

Mapping Water Quality Parameters in Urban Rivers from Hyperspectral Images Using a New Self-Adapting Selection of Multiple Artificial Neural Networks

Utilização de imagens de satélite para predição de clorofila-a e sólidos suspensos em corpos d\'água: estudo de caso da Represa do Lobo/SP

Contact Info

Product

Resources

About