Show simple item record

dc.contributor.authorHakala, Taina
dc.contributor.authorPölönen, Ilkka
dc.contributor.authorHonkavaara, Eija
dc.contributor.authorNäsi, Roope
dc.contributor.authorHakala, Teemu
dc.contributor.authorLindfors, Antti
dc.contributor.editorDiez, Pedro
dc.contributor.editorNeittaanmäki, Pekka
dc.contributor.editorPeriaux, Jacques
dc.contributor.editorTuovinen, Tero
dc.contributor.editorPons-Prats, Jordi
dc.date.accessioned2021-02-08T12:59:16Z
dc.date.available2021-02-08T12:59:16Z
dc.date.issued2020
dc.identifier.citationHakala, T., Pölönen, I., Honkavaara, E., Näsi, R., Hakala, T., & Lindfors, A. (2020). Using Aerial Platforms in Predicting Water Quality Parameters from Hyperspectral Imaging Data with Deep Neural Networks. In P. Diez, P. Neittaanmäki, J. Periaux, T. Tuovinen, & J. Pons-Prats (Eds.), <i>Computation and Big Data for Transport : Digital Innovations in Surface and Air Transport Systems</i> (pp. 213-238). Springer. Computational Methods in Applied Sciences, 54. <a href="https://doi.org/10.1007/978-3-030-37752-6_13" target="_blank">https://doi.org/10.1007/978-3-030-37752-6_13</a>
dc.identifier.otherCONVID_34840937
dc.identifier.urihttps://jyx.jyu.fi/handle/123456789/74035
dc.description.abstractIn near future it is assumable that automated unmanned aerial platforms are coming more common. There are visions that transportation of different goods would be done with large planes, which can handle over 1000 kg payloads. While these planes are used for transportation they could similarly be used for remote sensing applications by adding sensors to the planes. Hyperspectral imagers are one this kind of sensor types. There is need for the efficient methods to interpret hyperspectral data to the wanted water quality parameters. In this work we survey the performance of neural networks in the prediction of water quality parameters from remotely sensed hyperspectral data in freshwater basins. The hyperspectral data consists of 36 bands in the wavelength range of 508–878 nm and the water quality parameters to be predicted are temperature, conductivity, turbidity, Secchi depth, blue-green algae, chlorophyll-a, total phosphorus, acidity and dissolved oxygen. The objective of this investigation was to study the behaviour of different types of neural networks with this kind of data. Study is a survey of the operation of neural networks on this problem, which can be used as a basis for the design of a more comprehensive study. The neural network types examined were multilayer perceptron and 1-, 2- and 3-dimensional convolutional neural networks with the effect of scaling the hyperspectral data with standard or min-max -scaler recorded. We also investigated investigated how the prediction of individual water quality parameter depends on whether the neural network model is done solely with respect to this one parameter or with several parameters predicted simultaneously with the same model. The results of the correspondence between the predicted and measured water quality parameters were presented with normalized root mean square error, Pearson correlation coefficient and coefficient of determination. The best models were obtained the 2-dimensional convolutional neural networks with standard scaling made separately for each parameter. The parameters showing good predictability were conductivity, turbidity, Secchi-depth, blue-green algae, chlorophyll-a and total phosphorus, for which the coefficient of determination was at least 0.96 (apart from Secchi-depth even 0.98).en
dc.format.extent250
dc.format.mimetypeapplication/pdf
dc.languageeng
dc.language.isoeng
dc.publisherSpringer
dc.relation.ispartofComputation and Big Data for Transport : Digital Innovations in Surface and Air Transport Systems
dc.relation.ispartofseriesComputational Methods in Applied Sciences
dc.rightsIn Copyright
dc.subject.otherremote sensing
dc.subject.otherhyperspectral
dc.subject.otherwater quality
dc.subject.otherconvolutional neural networks
dc.titleUsing Aerial Platforms in Predicting Water Quality Parameters from Hyperspectral Imaging Data with Deep Neural Networks
dc.typebookPart
dc.identifier.urnURN:NBN:fi:jyu-202102081477
dc.contributor.laitosInformaatioteknologian tiedekuntafi
dc.contributor.laitosFaculty of Information Technologyen
dc.contributor.oppiaineTietotekniikkafi
dc.contributor.oppiaineMathematical Information Technologyen
dc.type.urihttp://purl.org/eprint/type/BookItem
dc.relation.isbn978-3-030-37751-9
dc.type.coarhttp://purl.org/coar/resource_type/c_3248
dc.description.reviewstatuspeerReviewed
dc.format.pagerange213-238
dc.relation.issn1871-3033
dc.type.versionacceptedVersion
dc.rights.copyright© Springer Nature Switzerland AG 2020
dc.rights.accesslevelopenAccessfi
dc.subject.ysovedenlaatu
dc.subject.ysokaukokartoitus
dc.subject.ysospektrikuvaus
dc.subject.ysoneuroverkot
dc.subject.ysovesien tila
dc.subject.ysoilmakuvakartoitus
dc.format.contentfulltext
jyx.subject.urihttp://www.yso.fi/onto/yso/p15738
jyx.subject.urihttp://www.yso.fi/onto/yso/p2521
jyx.subject.urihttp://www.yso.fi/onto/yso/p26364
jyx.subject.urihttp://www.yso.fi/onto/yso/p7292
jyx.subject.urihttp://www.yso.fi/onto/yso/p37934
jyx.subject.urihttp://www.yso.fi/onto/yso/p2520
dc.rights.urlhttp://rightsstatements.org/page/InC/1.0/?language=en
dc.relation.doi10.1007/978-3-030-37752-6_13
jyx.fundinginformationThis research has been co-funded by Finnish Funding Agency for Innovation Tekes (grants 2208/31/2013 and 1711/31/2016).
dc.type.okmA3


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

In Copyright
Except where otherwise noted, this item's license is described as In Copyright