This page has only limited features, please log in for full access.

Dr. Sina Keller
Karlsruhe Institute for Technology (KIT)

Basic Info


Research Keywords & Expertise

0 Data Science
0 GIS Application
0 Machine Learning
0 Remote Sensing
0 Artifical Intelligence

Honors and Awards

The user has no records in this section


Career Timeline

The user has no records in this section.


Short Biography

The user biography is not available.
Following
Followers
Co Authors
The list of users this user is following is empty.
Following: 0 users

Feed

Project

Project Goal: The objective of the joint research project ZEBBRA is the development of a non-invasive, mobile and innovative measurement and method approach to detect and analyse the condition of bridges during operation combined with an evaluation of the bridges' condition. The ZEBBRA project is funded within the scope "Forschung für die zivile Sicherheit 2012 bis 2017" in the specific topic civil security and infrastructure. Within the project part of the Institute of Photogrammetry and Remote Sensing (IPF) a monitoring approach for bridges based on GBR is developed. The objective is to detect changes or damages of the bridge structure. In contrast to traditional sensors, the GBR is capable of remotely measuring the displacement of several bridge points at the same time (see figure 1). As it reaches a sampling frequency of up to 200 Hz, the vibration of the bridge due to vehicles passing over it can be observed (see figure 2). The GBR-based monitoring approach is then evaluated and compared to directly contacting sensor data.

Starting Date:01 August 2018

Current Stage: Ongoing

0 Reads
Project

Project Goal: 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.

Starting Date:01 May 2017

Current Stage: Finished

0 Reads
Journal article
Published: 17 June 2021 in Processes
Reads 0
Downloads 0

The recycling of zinc in the Waelz process is an important part of the efficient use of resources in the steel processing cycle. The pyro-metallurgical processing of zinc-containing wastes takes place in a Waelz rotary kiln. Various measured variables are available to monitor the process. The temperature of the kiln-shell is analyzed by an infrared kiln-shell-scanner. In this paper, methods are presented which eliminate external weather-related disturbances on the temperature measured by the kiln-shell-scanner using a weather model and which extend the monitoring of the regularly necessary melting process to remove accretions. For this purpose, an adapted sigmoid estimation is introduced for the melting process, which provides new information about the current process status and a forecast of the further development of the melting process. As an assistance system for the plant operator, this enables an efficient execution of the melting process and reduces downtimes.

ACS Style

Markus Vogelbacher; Sina Keller; Wolfgang Zehm; Jörg Matthes. Advanced Methods for Kiln-Shell Monitoring to Optimize the Waelz Process for Zinc Recycling. Processes 2021, 9, 1062 .

AMA Style

Markus Vogelbacher, Sina Keller, Wolfgang Zehm, Jörg Matthes. Advanced Methods for Kiln-Shell Monitoring to Optimize the Waelz Process for Zinc Recycling. Processes. 2021; 9 (6):1062.

Chicago/Turabian Style

Markus Vogelbacher; Sina Keller; Wolfgang Zehm; Jörg Matthes. 2021. "Advanced Methods for Kiln-Shell Monitoring to Optimize the Waelz Process for Zinc Recycling." Processes 9, no. 6: 1062.

Journal article
Published: 20 March 2021 in Sensors
Reads 0
Downloads 0

In this study, we further develop the processing of ground-based interferometric radar measurements for the application of bridge monitoring. Applying ground-based radar in such complex setups or long measurement durations requires advanced processing steps to receive accurate measurements. These steps involve removing external influences from the measurement and evaluating the measurement uncertainty during processing. External influences include disturbances caused by objects moving through the signal, static clutter from additional scatterers, and changes in atmospheric properties. After removing these influences, the line-of-sight displacement vectors, measured by multiple ground-based radars, are decomposed into three-dimensional displacement components. The advanced processing steps are applied exemplarily on measurements with two sensors at a prestressed concrete bridge near Coburg (Germany). The external influences are successfully removed, and two components of the three-dimensional displacement vector are determined. A measurement uncertainty of less than 0.1 mm is achieved for the discussed application.

ACS Style

Chris Michel; Sina Keller. Advancing Ground-Based Radar Processing for Bridge Infrastructure Monitoring. Sensors 2021, 21, 2172 .

AMA Style

Chris Michel, Sina Keller. Advancing Ground-Based Radar Processing for Bridge Infrastructure Monitoring. Sensors. 2021; 21 (6):2172.

Chicago/Turabian Style

Chris Michel; Sina Keller. 2021. "Advancing Ground-Based Radar Processing for Bridge Infrastructure Monitoring." Sensors 21, no. 6: 2172.

Journal article
Published: 16 February 2021 in Remote Sensing
Reads 0
Downloads 0

Information about the chlorophyll a concentration of inland water bodies is essential for water monitoring. This study focuses on estimating chlorophyll a with remote sensing data, and machine learning (ML) approaches on the real-world SpecWa dataset. We adapt and apply a one-dimensional convolutional neural network (1D CNN) as a deep learning architecture for the first time to address this estimation. Since such a DL approach requires a large amount of data for its training, we rely on simulation data generated by the Water Color Simulator (WASI). This simulation is prepared accordingly and includes a knowledge-based water composition with two origins of the chlorophyll a concentration. Therefore, the training data is independent of the real-world SpecWa dataset, which is challenging for any ML approach. We define two spectral downsampling approaches as a pre-processing step, representing the hyperspectral EnMAP satellite mission (SR-EnMAP) and the multispectral Sentinel-2 mission (SR-Sentinel). Subsequently, we train a Random Forest, an artificial neural network, a band-ratio approach, and the 1D CNN on the WASI-generated simulation training dataset. Finally, all ML models are evaluated on the real SpecWa dataset. For both downsampled data, the 1D CNN outperforms the other ML models. On the finer resolved SR-EnMAP data it achieves an R 2 = 81.9 % , R M S E = 12.4 μg L−1, and M A E = 6.7 μg L−1. Besides, the 1D CNN’s performance decreases on the SR-Sentinel data to R 2 = 62.4 % . When focusing on the individual water bodies of the SpecWa dataset, the most significant differences exist between natural and artificial water bodies. We discover that the applied models estimate the chlorophyll a concentration of most natural water bodies satisfyingly. In sum, the newly DL approach can estimate the chlorophyll a values of unknown inland water bodies successfully, although it is trained on an entire simulation dataset.

ACS Style

Philipp Maier; Sina Keller; Stefan Hinz. Deep Learning with WASI Simulation Data for Estimating Chlorophyll a Concentration of Inland Water Bodies. Remote Sensing 2021, 13, 718 .

AMA Style

Philipp Maier, Sina Keller, Stefan Hinz. Deep Learning with WASI Simulation Data for Estimating Chlorophyll a Concentration of Inland Water Bodies. Remote Sensing. 2021; 13 (4):718.

Chicago/Turabian Style

Philipp Maier; Sina Keller; Stefan Hinz. 2021. "Deep Learning with WASI Simulation Data for Estimating Chlorophyll a Concentration of Inland Water Bodies." Remote Sensing 13, no. 4: 718.

Journal article
Published: 28 December 2020 in Remote Sensing
Reads 0
Downloads 0

Land cover and its change are crucial for many environmental applications. This study focuses on the land cover classification and change detection with multitemporal and multispectral Sentinel-2 satellite data. To address the challenging land cover change detection task, we rely on two different deep learning architectures and selected pre-processing steps. For example, we define an excluded class and deal with temporal water shoreline changes in the pre-processing. We employ a fully convolutional neural network (FCN), and we combine the FCN with long short-term memory (LSTM) networks. The FCN can only handle monotemporal input data, while the FCN combined with LSTM can use sequential information (multitemporal). Besides, we provided fixed and variable sequences as training sequences for the combined FCN and LSTM approach. The former refers to using six defined satellite images, while the latter consists of image sequences from an extended training pool of ten images. Further, we propose measures for the robustness concerning the selection of Sentinel-2 image data as evaluation metrics. We can distinguish between actual land cover changes and misclassifications of the deep learning approaches with these metrics. According to the provided metrics, both multitemporal LSTM approaches outperform the monotemporal FCN approach, about 3 to 5 percentage points (p.p.). The LSTM approach trained on the variable sequences detects 3 p.p. more land cover changes than the LSTM approach trained on the fixed sequences. Besides, applying our selected pre-processing improves the water classification and avoids reducing the dataset effectively by 17.6%. The presented LSTM approaches can be modified to provide applicability for a variable number of image sequences since we published the code of the deep learning models. The Sentinel-2 data and the ground truth are also freely available.

ACS Style

Oliver Sefrin; Felix Riese; Sina Keller. Deep Learning for Land Cover Change Detection. Remote Sensing 2020, 13, 78 .

AMA Style

Oliver Sefrin, Felix Riese, Sina Keller. Deep Learning for Land Cover Change Detection. Remote Sensing. 2020; 13 (1):78.

Chicago/Turabian Style

Oliver Sefrin; Felix Riese; Sina Keller. 2020. "Deep Learning for Land Cover Change Detection." Remote Sensing 13, no. 1: 78.

Journal article
Published: 27 October 2020 in ISPRS International Journal of Geo-Information
Reads 0
Downloads 0

Average speed information, which is essential for routing applications, is often missing in the freely available OpenStreetMap (OSM) road network. In this contribution, we propose an estimation framework, including different machine learning (ML) models that estimate rural roads’ average speed based on current road information in OSM. We rely on three datasets covering two regions in Chile and Australia. Google Directions API data serves as reference data. An appropriate estimation framework is presented, which involves supervised ML models, unsupervised clustering, and dimensionality reduction to generate new input features. The regression performance of each model with different input feature modes is evaluated on each dataset. The best performing model results in a coefficient of determination R2=80.43%, which is significantly better than previous approaches relying on domain-knowledge. Overall, the potential of the ML-based estimation framework to estimate the average speed with OSM road network data is demonstrated. This ML-based approach is data-driven and does not require any domain knowledge. In the future, we intend to focus on the generalization ability of the estimation framework concerning its application in different regions worldwide. The implementation of our estimation framework for an exemplary dataset is provided on GitHub.

ACS Style

Sina Keller; Raoul Gabriel; Johanna Guth. Machine Learning Framework for the Estimation of Average Speed in Rural Road Networks with OpenStreetMap Data. ISPRS International Journal of Geo-Information 2020, 9, 638 .

AMA Style

Sina Keller, Raoul Gabriel, Johanna Guth. Machine Learning Framework for the Estimation of Average Speed in Rural Road Networks with OpenStreetMap Data. ISPRS International Journal of Geo-Information. 2020; 9 (11):638.

Chicago/Turabian Style

Sina Keller; Raoul Gabriel; Johanna Guth. 2020. "Machine Learning Framework for the Estimation of Average Speed in Rural Road Networks with OpenStreetMap Data." ISPRS International Journal of Geo-Information 9, no. 11: 638.

Preprint
Published: 26 October 2020
Reads 0
Downloads 0

In this paper, we introduce a non-invasive approach for monitoring bridge infrastructure with ground-based interferometric radar. This approach is called the mirror mode, since it utilises the flat surface of the bridge underside as a mirror to reflect the signal to a corner reflector on the ground placed opposite of the radar sensor. For proving the feasibility of this approach, a measurement campaign has been carried out at an exemplary bridge in Karlsruhe (Germany) including a radar sensor in mirror mode, a second radar sensor in the default mode and a laser profile scanner. We investigate the potential of this approach to monitor the bridge displacement in vertical direction and compare the results with the two other sensors. The derived results reveal the potential for monitoring bridge infrastructure. Finally, we propose further research aspects of this approach to analyse its capabilities and limitation in the context of non-invasive infrastructure monitoring.

ACS Style

Chris Michel; Sina Keller. Introducing a Non-Invasive Monitoring Approach for Bridge Infrastructure with Ground-Based Interferometric Radar. 2020, 1 .

AMA Style

Chris Michel, Sina Keller. Introducing a Non-Invasive Monitoring Approach for Bridge Infrastructure with Ground-Based Interferometric Radar. . 2020; ():1.

Chicago/Turabian Style

Chris Michel; Sina Keller. 2020. "Introducing a Non-Invasive Monitoring Approach for Bridge Infrastructure with Ground-Based Interferometric Radar." , no. : 1.

Journal article
Published: 03 August 2020 in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Reads 0
Downloads 0

In this paper, we investigate the potential of detecting and classifying vehicle crossings (events) on bridges with ground-based interferometric radar (GBR) data and machine learning (ML) approaches. The GBR data and image data recorded by a unmanned aerial vehicle, used as ground truth, have been measured during field campaigns at three bridges in Germany non-invasively. Since traffic load of the bridges has taken place during the measurement, we have been able to monitor the bridge dynamics in terms of a vertical displacement. We introduce a methodological approach with three steps including preprocessing of the GBR data, feature extraction and well-chosen ML models. The impact of the preprocessing approaches as well as of the selected features on the classification results is evaluated. In case of the distinction between event and no event, adaptive boosting with low-pass filtering achieves the best classification results. Regarding the distinction between different class types of vehicles, random forest performs best utilising low-pass filtered GBR data. Our results reveal the potential of the GBR data combined with the respective methodological approach to detect and to classify events under real-world conditions. In conclusion, the preliminary results of this paper provide a basis for further improvements such as advanced preprocessing of the GBR data to extracted additional features which then can be used as input for the ML models.

ACS Style

M. Arnold; S. Keller. DETECTION AND CLASSIFICATION OF BRIDGE CROSSING EVENTS WITH GROUND-BASED INTERFEROMETRIC RADAR DATA AND MACHINE LEARNING APPROACHES. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2020, V-1-2020, 109 -116.

AMA Style

M. Arnold, S. Keller. DETECTION AND CLASSIFICATION OF BRIDGE CROSSING EVENTS WITH GROUND-BASED INTERFEROMETRIC RADAR DATA AND MACHINE LEARNING APPROACHES. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2020; V-1-2020 ():109-116.

Chicago/Turabian Style

M. Arnold; S. Keller. 2020. "DETECTION AND CLASSIFICATION OF BRIDGE CROSSING EVENTS WITH GROUND-BASED INTERFEROMETRIC RADAR DATA AND MACHINE LEARNING APPROACHES." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences V-1-2020, no. : 109-116.

Chapter
Published: 28 April 2020 in Guide to 3D Vision Computation
Reads 0
Downloads 0

In this chapter, we present an entire workflow for hyperspectral regression based on supervised, semi-supervised, and unsupervised learning. Hyperspectral regression is defined as the estimation of continuous parameters like chlorophyll a, soil moisture, or soil texture based on hyperspectral input data. The main challenges in hyperspectral regression are the high dimensionality and strong correlation of the input data combined with small ground truth datasets as well as dataset shift. The presented workflow is divided into three levels. (1) At the data level, the data is pre-processed, dataset shift is addressed, and the dataset is split reasonably. (2) The feature level considers unsupervised dimensionality reduction, unsupervised clustering as well as manual feature engineering and feature selection. These unsupervised approaches include autoencoder (AE), t-distributed stochastic neighbor embedding (t-SNE) as well as uniform manifold approximation and projection (UMAP). (3) At the model level, the most commonly used supervised and semi-supervised machine learning models are presented. These models include random forests (RF), convolutional neural networks (CNN), and supervised self-organizing maps (SOM). We address the process of model selection, hyperparameter optimization, and model evaluation. Finally, we give an overview of upcoming trends in hyperspectral regression. Additionally, we provide comprehensive code examples and accompanying materials in the form of a hyperspectral dataset and Python notebooks via GitHub [98, 100].

ACS Style

Felix Riese; Sina Keller. Supervised, Semi-supervised, and Unsupervised Learning for Hyperspectral Regression. Guide to 3D Vision Computation 2020, 187 -232.

AMA Style

Felix Riese, Sina Keller. Supervised, Semi-supervised, and Unsupervised Learning for Hyperspectral Regression. Guide to 3D Vision Computation. 2020; ():187-232.

Chicago/Turabian Style

Felix Riese; Sina Keller. 2020. "Supervised, Semi-supervised, and Unsupervised Learning for Hyperspectral Regression." Guide to 3D Vision Computation , no. : 187-232.

Journal article
Published: 17 January 2020 in ISPRS International Journal of Geo-Information
Reads 0
Downloads 0

Average speed is crucial for calculating link travel time to find the fastest path in a road network. However, readily available data sources like OpenStreetMap (OSM) often lack information about the average speed of a road. However, OSM contains other road information which enables an estimation of average speed in rural regions. In this paper, we develop a Fuzzy Framework for Speed Estimation (Fuzzy-FSE) that employs fuzzy control to estimate average speed based on the parameters road class, road slope, road surface and link length. The OSM road network and, optionally, a digital elevation model (DEM) serve as free-to-use and worldwide available input data. The Fuzzy-FSE consists of two parts: (a) a rule and knowledge base which decides on the output membership functions and (b) multiple Fuzzy Control Systems which calculate the output average speeds. The Fuzzy-FSE is applied exemplary and evaluated for the BioBío and Maule region in central Chile and for the north of New South Wales in Australia. Results demonstrate that, even using only OSM data, the Fuzzy-FSE performs better than existing methods such as fixed speed profiles. Compared to these methods, the Fuzzy-FSE improves the speed estimation between 2% to 12%. In future work, we will investigate the potential of data-driven machine learning methods to estimate average speed. The applied datasets and the source code of the Fuzzy-FSE are available via GitHub.

ACS Style

Johanna Guth; Sven Wursthorn; Sina Keller. Multi-Parameter Estimation of Average Speed in Road Networks Using Fuzzy Control. ISPRS International Journal of Geo-Information 2020, 9, 55 .

AMA Style

Johanna Guth, Sven Wursthorn, Sina Keller. Multi-Parameter Estimation of Average Speed in Road Networks Using Fuzzy Control. ISPRS International Journal of Geo-Information. 2020; 9 (1):55.

Chicago/Turabian Style

Johanna Guth; Sven Wursthorn; Sina Keller. 2020. "Multi-Parameter Estimation of Average Speed in Road Networks Using Fuzzy Control." ISPRS International Journal of Geo-Information 9, no. 1: 55.

Journal article
Published: 11 January 2020 in International Journal of Disaster Risk Reduction
Reads 0
Downloads 0

Research on evacuation behavior in natural disasters provides a valuable contribution in the development of effective short- and long-term strategies in disaster risk management (DRM). Many studies address evacuation simulation utilizing mathematical modeling approaches or GIS-based simulation. In this contribution, we perform a detailed analysis of an entire evacuation process from the decision to evacuate right up to the arrival at a safe zone. We apply a progressive research design in the community of Talcahuano, Chile by means of linking a social science approach, deploying standardized questionnaires for the tsunami affected population, and a GIS-based simulation. The questionnaire analyzes evacuation behavior in both an event-based historical scenario and a hypothetical future scenario. Results reveal three critical issues: evacuation time, distance to the evacuation zone, and method of transportation. In particular, the excessive use of cars has resulted in congestion of street sections in past evacuations, and will most probably also pose a problem in a future evacuation event. As evacuation by foot is generally recommended by DRM, the results are extended by a GIS-based modeling simulating evacuation by foot. Combining the findings of both approaches allows for added value, providing more comprehensive insights into evacuation planning. Future research may take advantage of this multi-perspective research design, and integrate social science findings in a more detailed manner. Making use of invaluable local knowledge and past experience of the affected population in evacuation planning is likely to help decrease the magnitude of a disaster, and, ultimately, save lives.

ACS Style

Susanne Kubisch; Johanna Guth; Sina Keller; Maria T. Bull; Lars Keller; Andreas Ch. Braun. The contribution of tsunami evacuation analysis to evacuation planning in Chile: Applying a multi-perspective research design. International Journal of Disaster Risk Reduction 2020, 45, 101462 .

AMA Style

Susanne Kubisch, Johanna Guth, Sina Keller, Maria T. Bull, Lars Keller, Andreas Ch. Braun. The contribution of tsunami evacuation analysis to evacuation planning in Chile: Applying a multi-perspective research design. International Journal of Disaster Risk Reduction. 2020; 45 ():101462.

Chicago/Turabian Style

Susanne Kubisch; Johanna Guth; Sina Keller; Maria T. Bull; Lars Keller; Andreas Ch. Braun. 2020. "The contribution of tsunami evacuation analysis to evacuation planning in Chile: Applying a multi-perspective research design." International Journal of Disaster Risk Reduction 45, no. : 101462.

Journal article
Published: 18 December 2019 in Remote Sensing
Reads 0
Downloads 0

Machine learning approaches are valuable methods in hyperspectral remote sensing, especially for the classification of land cover or for the regression of physical parameters. While the recording of hyperspectral data has become affordable with innovative technologies, the acquisition of reference data (ground truth) has remained expensive and time-consuming. There is a need for methodological approaches that can handle datasets with significantly more hyperspectral input data than reference data. We introduce the Supervised Self-organizing Maps (SuSi) framework, which can perform unsupervised, supervised and semi-supervised classification as well as regression on high-dimensional data. The methodology of the SuSi framework is presented and compared to other frameworks. Its different parts are evaluated on two hyperspectral datasets. The results of the evaluations can be summarized in four major findings: (1) The supervised and semi-Supervised Self-organizing Maps (SOM) outperform random forest in the regression of soil moisture. (2) In the classification of land cover, the supervised and semi-supervised SOM reveal great potential. (3) The unsupervised SOM is a valuable tool to understand the data. (4) The SuSi framework is versatile, flexible, and easy to use. The SuSi framework is provided as an open-source Python package on GitHub.

ACS Style

Felix M. Riese; Sina Keller; Stefan Hinz. Supervised and Semi-Supervised Self-Organizing Maps for Regression and Classification Focusing on Hyperspectral Data. Remote Sensing 2019, 12, 7 .

AMA Style

Felix M. Riese, Sina Keller, Stefan Hinz. Supervised and Semi-Supervised Self-Organizing Maps for Regression and Classification Focusing on Hyperspectral Data. Remote Sensing. 2019; 12 (1):7.

Chicago/Turabian Style

Felix M. Riese; Sina Keller; Stefan Hinz. 2019. "Supervised and Semi-Supervised Self-Organizing Maps for Regression and Classification Focusing on Hyperspectral Data." Remote Sensing 12, no. 1: 7.

Conference paper
Published: 01 September 2019 in 2019 10th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS)
Reads 0
Downloads 0
ACS Style

Philipp M. Maier; Sina Keller. 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) 2019, 1 .

AMA Style

Philipp M. Maier, Sina Keller. 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). 2019; ():1.

Chicago/Turabian Style

Philipp M. Maier; Sina Keller. 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) , no. : 1.

Original paper
Published: 01 July 2019 in Natural Hazards
Reads 0
Downloads 0

Natural hazards such as earthquakes, floods, or wildfires pose a serious threat to road infrastructure. Especially in emergency situations, the society depends on the road infrastructure to maintain its functionality in terms of evacuation and accessibility to emergency facilities. In this paper, we develop a generic, multi-scale concept to analyze the accessibility to emergency facilities in critical road infrastructure for natural disaster scenarios. We follow a modular approach: The basic module evaluates the accessibility of emergency facilities by calculating an accessibility index. Other modules enable the calculation of a grid-based index and the generation of a degraded network based on a natural disaster scenario. OpenStreetMap serves as a free-to-use and worldwide available database for the road network and the emergency facility location. The concept is applied exemplarily for two wildfire scenarios of different geographic scales: the January 2017 Wildfires in the BioBío and Maule region located in central Chile and the June 2017 Wildfires in central Portugal. An impact analysis of the wildfires on the accessibility of emergency facilities is performed and evaluated. As a result, the concept provides a valuable and data-sparse decision aid tool for regional planners and disaster control. It can be used in different stages of the disaster risk management cycle. In the mitigation and preparation phase, places with poor accessibility can be identified. In the short-term response phase after a disaster, the quick identification of critical and disconnected road network parts assists disaster control in planning a possible reaction strategy.

ACS Style

Johanna Guth; Sven Wursthorn; Andreas Ch. Braun; Sina Keller. Development of a generic concept to analyze the accessibility of emergency facilities in critical road infrastructure for disaster scenarios: exemplary application for the 2017 wildfires in Chile and Portugal. Natural Hazards 2019, 97, 979 -999.

AMA Style

Johanna Guth, Sven Wursthorn, Andreas Ch. Braun, Sina Keller. Development of a generic concept to analyze the accessibility of emergency facilities in critical road infrastructure for disaster scenarios: exemplary application for the 2017 wildfires in Chile and Portugal. Natural Hazards. 2019; 97 (3):979-999.

Chicago/Turabian Style

Johanna Guth; Sven Wursthorn; Andreas Ch. Braun; Sina Keller. 2019. "Development of a generic concept to analyze the accessibility of emergency facilities in critical road infrastructure for disaster scenarios: exemplary application for the 2017 wildfires in Chile and Portugal." Natural Hazards 97, no. 3: 979-999.

Journal article
Published: 05 June 2019 in ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Reads 0
Downloads 0
ACS Style

M. Weinmann; R. Müller; R. Reulke; E. Honkavaara; D. Tuia; S. Keller. PREFACE – ISPRS WORKSHOP HYPERSPECTRAL SENSING MEETS MACHINE LEARNING AND PATTERN ANALYSIS (HYPERMLPA 2019). ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2019, XLII-2/W13, 1825 -1826.

AMA Style

M. Weinmann, R. Müller, R. Reulke, E. Honkavaara, D. Tuia, S. Keller. PREFACE – ISPRS WORKSHOP HYPERSPECTRAL SENSING MEETS MACHINE LEARNING AND PATTERN ANALYSIS (HYPERMLPA 2019). ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2019; XLII-2/W13 ():1825-1826.

Chicago/Turabian Style

M. Weinmann; R. Müller; R. Reulke; E. Honkavaara; D. Tuia; S. Keller. 2019. "PREFACE – ISPRS WORKSHOP HYPERSPECTRAL SENSING MEETS MACHINE LEARNING AND PATTERN ANALYSIS (HYPERMLPA 2019)." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-2/W13, no. : 1825-1826.

Journal article
Published: 29 May 2019 in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Reads 0
Downloads 0

Soil texture is important for many environmental processes. In this paper, we study the classification of soil texture based on hyperspectral data. We develop and implement three 1-dimensional (1D) convolutional neural networks (CNN): the LucasCNN, the LucasResNet which contains an identity block as residual network, and the LucasCoordConv with an additional coordinates layer. Furthermore, we modify two existing 1D CNN approaches for the presented classification task. The code of all five CNN approaches is available on GitHub (Riese, 2019). We evaluate the performance of the CNN approaches and compare them to a random forest classifier. Thereby, we rely on the freely available LUCAS topsoil dataset. The CNN approach with the least depth turns out to be the best performing classifier. The LucasCoordConv achieves the best performance regarding the average accuracy. In future work, we can further enhance the introduced LucasCNN, LucasResNet and LucasCoordConv and include additional variables of the rich LUCAS dataset.

ACS Style

Felix Riese; S. Keller. SOIL TEXTURE CLASSIFICATION WITH 1D CONVOLUTIONAL NEURAL NETWORKS BASED ON HYPERSPECTRAL DATA. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2019, IV-2/W5, 615 -621.

AMA Style

Felix Riese, S. Keller. SOIL TEXTURE CLASSIFICATION WITH 1D CONVOLUTIONAL NEURAL NETWORKS BASED ON HYPERSPECTRAL DATA. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2019; IV-2/W5 ():615-621.

Chicago/Turabian Style

Felix Riese; S. Keller. 2019. "SOIL TEXTURE CLASSIFICATION WITH 1D CONVOLUTIONAL NEURAL NETWORKS BASED ON HYPERSPECTRAL DATA." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences IV-2/W5, no. : 615-621.

Journal article
Published: 29 May 2019 in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Reads 0
Downloads 0
ACS Style

M. Weinmann; R. Müller; R. Reulke; E. Honkavaara; D. Tuia; S. Keller. PREFACE – HYPERSPECTRAL SENSING MEETS MACHINE LEARNING AND PATTERN ANALYSIS (HYPERMLPA 2019). ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2019, IV-2/W5, 607 -608.

AMA Style

M. Weinmann, R. Müller, R. Reulke, E. Honkavaara, D. Tuia, S. Keller. PREFACE – HYPERSPECTRAL SENSING MEETS MACHINE LEARNING AND PATTERN ANALYSIS (HYPERMLPA 2019). ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2019; IV-2/W5 ():607-608.

Chicago/Turabian Style

M. Weinmann; R. Müller; R. Reulke; E. Honkavaara; D. Tuia; S. Keller. 2019. "PREFACE – HYPERSPECTRAL SENSING MEETS MACHINE LEARNING AND PATTERN ANALYSIS (HYPERMLPA 2019)." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences IV-2/W5, no. : 607-608.

Journal article
Published: 29 May 2019 in ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Reads 0
Downloads 0

Water is a key component of life, the natural environment and human health. For monitoring the conditions of a water body, the chlorophyll a concentration can serve as a proxy for nutrients and oxygen supply. In situ measurements of water quality parameters are often time-consuming, expensive and limited in areal validity. Therefore, we apply remote sensing techniques. During field campaigns, we collected hyperspectral data with a spectrometer and in situ measured chlorophyll a concentrations of 13 inland water bodies with different spectral characteristics. One objective of this study is to estimate chlorophyll a concentrations of these inland waters by applying three machine learning regression models: Random Forest, Support Vector Machine and an Artificial Neural Network. Additionally, we simulate four different hyperspectral resolutions of the spectrometer data to investigate the effects on the estimation performance. Furthermore, the application of first order derivatives of the spectra is evaluated in turn to the regression performance. This study reveals the potential of combining machine learning approaches and remote sensing data for inland waters. Each machine learning model achieves an R2-score between 80% to 90% for the regression on chlorophyll a concentrations. The random forest model benefits clearly from the applied derivatives of the spectra. In further studies, we will focus on the application of machine learning models on spectral satellite data to enhance the area-wide estimation of chlorophyll a concentration for inland waters.

ACS Style

P. M. Maier; S. Keller. ESTIMATING CHLOROPHYLL A CONCENTRATIONS OF SEVERAL INLAND WATERS WITH HYPERSPECTRAL DATA AND MACHINE LEARNING MODELS. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences 2019, IV-2/W5, 609 -614.

AMA Style

P. M. Maier, S. Keller. ESTIMATING CHLOROPHYLL A CONCENTRATIONS OF SEVERAL INLAND WATERS WITH HYPERSPECTRAL DATA AND MACHINE LEARNING MODELS. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences. 2019; IV-2/W5 ():609-614.

Chicago/Turabian Style

P. M. Maier; S. Keller. 2019. "ESTIMATING CHLOROPHYLL A CONCENTRATIONS OF SEVERAL INLAND WATERS WITH HYPERSPECTRAL DATA AND MACHINE LEARNING MODELS." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences IV-2/W5, no. : 609-614.

Conference paper
Published: 01 January 2019 in Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management
Reads 0
Downloads 0
ACS Style

J. Stötzer; S. Wursthorn; Sina Keller. Fuzzy Estimation of Link Travel Time from a Digital Elevation Model and Road Hierarchy Level. Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management 2019, 15 -25.

AMA Style

J. Stötzer, S. Wursthorn, Sina Keller. Fuzzy Estimation of Link Travel Time from a Digital Elevation Model and Road Hierarchy Level. Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management. 2019; ():15-25.

Chicago/Turabian Style

J. Stötzer; S. Wursthorn; Sina Keller. 2019. "Fuzzy Estimation of Link Travel Time from a Digital Elevation Model and Road Hierarchy Level." Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management , no. : 15-25.