Application Of Different Simulated Spectral Data And Machine Learning To Estimate The Chlorophyll A Concentration Of Several Inland Waters

Water quality is of great importance for humans and for the environment and hence has to be monitored continuously. One possibility are proxies such as the chlorophyll a concentration, which can be monitored by remote sensing techniques. This study focuses on the trade-off between the spatial and the spectral resolution of six simulated satellite-based data sets when estimating the chlorophyll a concentration with supervised machine learning models. The initial dataset for the spectral simulation of the satellite missions contains spectrometer data and measured chlorophyll a concentration of 13 different inland waters. The analysis of the regression performance indicates, that the machine learning models achieve almost as good results with the simulated Sentinel data as with the simulated hyperspectral data. Re-grading the applicability, the Sentinel 2 mission is the best choice for small inland waters due to its high spatial and temporal resolution in combination with a suitable spectral resolution.

[1]  L. Vilas,et al.  Neural network estimation of chlorophyll a from MERIS full resolution data for the coastal waters of Galician rias (NW Spain) , 2011 .

[2]  M. Kahru,et al.  Ocean Color Chlorophyll Algorithms for SEAWIFS , 1998 .

[3]  Susanna T. Y. Tong,et al.  Comparison of satellite reflectance algorithms for estimating chlorophyll-a in a temperate reservoir using coincident hyperspectral aircraft imagery and dense coincident surface observations , 2016 .

[4]  Yoshua Bengio,et al.  Pattern Recognition and Neural Networks , 1995 .

[5]  Sina Keller,et al.  Machine Learning Regression on Hyperspectral Data to Estimate Multiple Water Parameters , 2018, 2018 9th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS).

[6]  H. Gons,et al.  Optical teledetection of chlorophyll a in turbid inland waters , 1999 .

[7]  Jerome H. Friedman.  Multivariate adaptive regression splines (with discussion) , 1991 .

[8]  Vladimir Vapnik,et al.  The Nature of Statistical Learning , 1995 .

[9]  Sampsa Koponen,et al.  Lake water quality classification with airborne hyperspectral spectrometer and simulated MERIS data , 2002 .

[10]  Stephanie C. J. Palmer,et al.  Remote sensing of inland waters: Challenges, progress and future directions , 2015 .

[11]  Xiao‐Hai Yan,et al.  A Neural Network Model for Estimating Sea Surface Chlorophyll and Sediments from Thematic Mapper Imagery , 1998 .

[12]  Stefan Hinz,et al.  Hyperspectral Data and Machine Learning for Estimating CDOM, Chlorophyll a, Diatoms, Green Algae and Turbidity , 2018, International journal of environmental research and public health.

[13]  Tim J. Malthus,et al.  The effect of spectral bandwidth and positioning on the spectral signature analysis of inland waters , 1992 .

[14]  Sina Keller,et al.  Estimating Chlorophyll a Concentrations of Several Inland Waters with Hyperspectral Data and Machine Learning Models , 2019, ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences.

[15]  Guido Pasquariello,et al.  A Specialized Support Vector Machine for Coastal Water Chlorophyll Retrieval from Water Leaving Reflectances , 2008, IGARSS 2008 - 2008 IEEE International Geoscience and Remote Sensing Symposium.

[16]  Anatoly A. Gitelson,et al.  The peak near 700 nm on radiance spectra of algae and water: relationships of its magnitude and position with chlorophyll concentration , 1992 .

[17]  J. Friedman.  Multivariate adaptive regression splines , 1990 .

[18]  S. Hinz,et al.  Estimation of Chlorophyll a, Diatoms and Green Algae Based on Hyperspectral Data with Machine Learning Approaches , 2018 .

[19]  L. Prieur,et al.  Analysis of variations in ocean color1 , 1977 .

[20]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.