TRUST: Sustainable, fair and ecologically compatible drinking water supply in prosperous water-shortage regions

contact: Felix Riese, M.Sc.
Dr. rer.nat. Sina Keller
Prof. Dr.-Ing. Stefan Hinz
funding: Federal Ministry of Education and Research (BMBF)
Partner: University of Stuttgart, DVWG - Water Technology Center (TWZ), Decon International GmbH,, Disy Informationssysteme GmbH, Pabsch & Partner Ingenieurgesellschaft mbH, OTT Hydromet GmbH
startdate: 01.05.2017
enddate: 30.04.2020

In the TRUST project, planning and problem solving tools are developed to achieve the United Nations "Sustainable Development Goal" concerned with water and sanitation (UN SDG No. 6). Generic models, that are developed in the scope of this project, are applied exemplary to the catchment of the region Lima/Peru.

At the Karlsruhe Institute of Technology (KIT), the Institute of Photogrammetry and Remote Sensing (IPF) and the Institute of Water and River Basin Management (IWG) are in charge of both monitoring the water balance variables and applyling a hydrological model. The three overall objectives are a) the combination of terrestrial observations and remote sensing data for the representative study of water balance variables, b) the hydrological system analysis and regionalization of water balance variables, especially the precipitation and soil-moisture dynamics, and c) the comprehensive derivation of land use, soil and geometric data.

At the IPF, we are responsible for the following tasks:

Developing a digital terrain model, from which correct watersheds, river courses and catchment areas can be extracted automatically. Furthermore, their temporal change will be monitored.
Developing and implementing a (spacial- & temporal-) context-based classiﬁer, from whichthe general type and the temporal change of the land use can be monitored.
Developing and implementing descriptors speciﬁcally designed for irrigated areas.
Developing a image analysis methods to derive the soil type in the project region.
Characterizing the water hygiene by deriving parameters of spectral signatures from hyperspectral data.

In terms of hardware, hyperspectral cameras (e.g. in the SWIR spectrum, 950nm - 2500nm) are being used statically and on ﬂexible small platforms like drones. Furthermore, there are plans to expand the local measurements on a global scale through the EnMAP satellite mission (400nm - 2500nm).

Further information:

Publications

2021

Maier, P.; Keller, S.; Hinz, S. (2021). Deep Learning with WASI Simulation Data for Estimating Chlorophyll a Concentration of Inland Water Bodies. Remote sensing, 13 (4), 718. doi:10.3390/rs13040718
Maier, P. M. (2021, December 16). Towards a Generalized Machine Learning Approach for Estimating Chlorophyll Values in Inland Waters with Spectral Data. PhD dissertation. Karlsruher Institut für Technologie (KIT). doi:10.5445/IR/1000141060
Sefrin, O.; Riese, F. M.; Keller, S. (2021). Deep Learning for Land Cover Change Detection. Remote sensing, 13 (1), Article no: 78. doi:10.3390/rs13010078

2020

Keller, S.; Riese, F. M.; Allroggen, N.; Jackisch, C. (2020, May). HydReSGeo: Field experiment dataset of surface-sub-surface infiltration dynamics acquired by hydrological, remote sensing, and geophysical measurement techniques. doi:10.5880/fidgeo.2020.015
Maier, P. M.; Keller, S. (2020). SpecWa: Spectral remote sensing data and chlorophyll a values of inland waters. doi:10.5880/fidgeo.2020.036
Riese, F. M. (2020). LUCAS Soil Texture Processing Scripts. doi:10.5281/zenodo.3871431
Riese, F. M. (2020). Processing Scripts of the ALPACA Dataset. doi:10.5281/zenodo.3871459
Riese, F. M. (2020, March). Hyperspectral Processing Scripts for the HydReSGeo Dataset 1.0.0. doi:10.5281/zenodo.3706418
Riese, F. M. (2020, June 10). Development and Applications of Machine Learning Methods for Hyperspectral Data. PhD dissertation. Karlsruher Institut für Technologie (KIT). doi:10.5445/IR/1000120067
Riese, F. M.; Keller, S. (2020). Supervised, Semi-supervised, and Unsupervised Learning for Hyperspectral Regression. Hyperspectral Image Analysis : Advances in Machine Learning and Signal Processing. Hrsg.: S. Prasad, 187–232, Springer Nature. doi:10.1007/978-3-030-38617-7_7
Riese, F. M.; Keller, S.; Hinz, S. (2020). Supervised and Semi-Supervised Self-Organizing Maps for Regression and Classification Focusing on Hyperspectral Data. Remote sensing, 12 (1), Art. Nr.: 7. doi:10.3390/rs12010007
Riese, F. M.; Schroers, S.; Wienhöfer, J.; Keller, S. (2020, April 9). Aerial Peruvian Andes Campaign (ALPACA) Dataset 2019. doi:10.5445/IR/1000118082
Sefrin, O.; Riese, F. M.; Keller, S. (2020). Code for Deep Learning for Land Cover Change Detection 1.0.1. doi:10.5281/zenodo.4289079
Wagner, P.; Riese, F. M.; Keller, S. (2020). CAOS Sentinel-2 Pipeline in Python. doi:10.5281/zenodo.3879622

2019

Leitloff, J.; Riese, F. M. (2019, May 15). Satellite Computer Vision mit Keras und Tensorflow - Best practices und Beispiele aus der Forschung. Minds Mastering Machines (2019), Mannheim, Germany, May 14–16, 2019. doi:10.5281/zenodo.4056744
León, C. D.; Kosow, H.; Zahumensky, Y.; Krauß, M.; Wasielewski, S.; Minke, R.; Wienhöfer, J.; Riese, F. M.; Keller, S.; Sturm, S.; Brauer, F.; Hügler, M.; Gottwalt, J.; Riepl, D. (2019). Solutions and planning tools for water supply and wastewater management in prosperous regions tackling water scarcity. Proceedings of the GRoW Midterm Conference - Global analyses and local solutions for sustainable water resources management, Frankfurt am Main, 20-21 February 2019. Ed.: A. Kramer, 28–31, adelphi.
Maier, P.; Keller, S. (2019). ESTIMATING CHLOROPHYLL A CONCENTRATIONS OF SEVERAL INLAND WATERS WITH HYPERSPECTRAL DATA AND MACHINE LEARNING MODELS. ISPRS Geospatial Week 2019, 10–14 June 2019, Enschede, The Netherlands. Ed.: G. Vosselman, 609–614, ISPRS. doi:10.5194/isprs-annals-IV-2-W5-609-2019
Maier, P. M.; Keller, S. (2019). Application Of Different Simulated Spectral Data And Machine Learning To Estimate The Chlorophyll A Concentration Of Several Inland Waters. Institute of Electrical and Electronics Engineers (IEEE).
Maier, P. M.; Keller, S. (2019). Application Of Different Simulated Spectral Data And Machine Learning To Estimate The Chlorophyll A Concentration Of Several Inland Waters. 2019 10th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS), 24-26 Sept. 2019, Amsterdam, Netherlands, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/WHISPERS.2019.8921073
Riese, F. M. (2019). Processing Scripts for Thermal Infrared Cameras. doi:10.5281/zenodo.3576242
Riese, F. M. (2019). SUSI: SUpervised Self-organIzing maps in Python. Zenodo. doi:10.5281/zenodo.2609130
Riese, F. M. (2019). CNN Soil Texture Classification. Zenodo. doi:10.5281/zenodo.2540718
Riese, F. M.; Keller, S. (2019). Hyperspectral Regression: Code Examples. doi:10.5281/zenodo.3450676
Riese, F. M.; Keller, S. (2019). SUSI: Supervised Self-Organizing Maps for Regression and Classification in Python.
Riese, F. M.; Keller, S. (2019). Soil Texture Classification with 1D Convolutional Neural Networks based on Hyperspectral Data. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences (2019 ISPRS) Geospatial Week 2019, Enschede, NL, June 10-14, 2019. Vol. IV-2/W5, 615–621. doi:10.5194/isprs-annals-IV-2-W5-615-2019
Sefrin, O.; Riese, F. M.; Keller, S. (2019). Soil Texture Processing. doi:10.5281/zenodo.3431628

2018

Keller, S.; Maier, P.; Riese, F.; Norra, S.; Holbach, A.; Börsig, N.; Wilhelms, A.; Moldaenke, C.; Zaake, A.; Hinz, S. (2018). Hyperspectral Data and Machine Learning for Estimating CDOM, Chlorophyll a, Diatoms, Green Algae and Turbidity. International journal of environmental research and public health, 15 (9), 1881/1–15. doi:10.3390/ijerph15091881
Keller, S.; Riese, F. M.; Allroggen, N.; Jackisch, C.; Hinz, S. (2018). Modeling Subsurface Soil Moisture Based on Hyperspectral Data : First Results of a Multilateral Field Campaign. Photogrammetrie, Fernerkundung, Geoinformatik, Kartographie 2018 (PFGK18) : Beiträge der 37. Wissenschaftlich-Technische Jahrestagung der DGPF e.V., 5. Münchner GI-Runde Runder Tisch GIS e.V. und des 66. Deutscher Kartographie Kongress der DGfK e.V., München, Deutschland, 7. - 9. März 2018. Hrsg.: T. P. Kersten, 34–48, Deutsche Gesellschaft für Photogrammetrie.
Keller, S.; Riese, F. M.; Stötzer, J.; Maier, P. M.; Hinz, S. (2018). Developing a machine learning framework for estimating soil moisture with VNIR hyperspectral data. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences - Symposium “Innovative Sensing – From Sensors to Methods and Applications”, Karlsruhe, Germany, 10–12 October 2018. Volume: IV-1, 101–108, ISPRS. doi:10.5194/isprs-annals-IV-1-101-2018
Leitloff, J.; Riese, F. M. (2018). Examples for CNN training and classification on Sentinel-2 data. doi:10.5281/zenodo.3268451
Maier, P. M.; Hinz, S.; Keller, S. (2018). Estimation of Chlorophyll a, Diatoms and Green Algae Based on Hyperspectral Data with Machine Learning Approaches. Photogrammetrie, Fernerkundung, Geoinformatik, Kartographie 2018 (PFGK18) : Beiträge der 37. Wissenschaftlich-Technische Jahrestagung der DGPF e.V., 5. Münchner GI-Runde Runder Tisch GIS e.V. und des 66. Deutscher Kartographie Kongress der DGfK e.V., München, Deutschland, 7. - 10. März 2018. Hrsg.: T. P. Kersten, 49–57, Deutsche Gesellschaft für Photogrammetrie.
Maier, P. M.; Keller, S. (2018). Machine learning regression on hyperspectral data to estimate multiple water parameters.
Riese, F. M.; Keller, S. (2018). Introducing a Framework of Self-Organizing Maps for Regression of Soil Moisture with Hyperspectral Data. IGARSS 2018 - 2018 IEEE International Geoscience and Remote Sensing Symposium, Valencia, Spain, 22nd - 27th July, 2018, 6151–6154, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/IGARSS.2018.8517812
Riese, F. M.; Keller, S. (2018, April 24). Hyperspectral benchmark dataset on soil moisture. doi:10.5281/zenodo.1227837
Riese, F. M.; Keller, S. (2018). Fusion of hyperspectral and ground penetrating radar data to estimate soil moisture. 9th Workshop on Hyperspectral Image and Signal Processing : Evolution in Remote Sensing (Whispers 2018), Amsterdam, NL, September 23-26, 2018, Institute of Electrical and Electronics Engineers (IEEE). doi:10.1109/WHISPERS.2018.8747076
Weinmann, M.; Maier, P. M.; Florath, J.; Weidner, U. (2018). Investigation on the potential of hyperspectral and Sentinel-2 data for land-cover / land-use classification. 2018 ISPRS Technical Commission I Midterm Symposium on Innovative Sensing - From Sensors to Methods and Applications; Karlsruhe; Germany; 10 October 2018 through 12 October 2018. Ed.: S. Hinz, 155–162, Curran. doi:10.5194/isprs-annals-IV-1-155-2018