Konstantin Klemmer
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Konstantin Klemmer has a total of 63 co-authors. Here are the top co-authors by number of shared publications:
- Esther Rolf
University of Colorado Boulder
3 shared publications - Hongkai Wen
University of Warwick, Coventry, United Kingdom
3 shared publications - Marc Rußwurm
Wageningen University
3 shared publications - Bowen Du
Tongji University, Shanghai, China
2 shared publications - Caleb Robinson
Microsoft AI for Good Research Lab, Redmond, WA, USA
2 shared publications - Daniel B. Neill
New York University, New York, NY, USA
2 shared publications
Latest Publications
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Magazine
- p. 2-15
Earth Embeddings: Toward artificial intelligence-centric representations of our planet
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Magazine
- p. 2-15
Open AccessEarth Embeddings: Toward artificial intelligence-centric representations of our planet
- Open Access
- 10 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Earth Embeddings: Harnessing the Information in Earth Observation Data with Machine Learning
- 10 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-2
Open AccessEarth Embeddings: Harnessing the Information in Earth Observation Data with Machine Learning
- Top Cited PapersOpen Access
- 15 May 2024
- Published by The Royal Society in Royal Society Open Science
- Vol. 11 (5) , 230859
Towards algorithm auditing: managing legal, ethical and technological risks of AI, ML and associated algorithms
Business reliance on algorithms is becoming ubiquitous, and companies are increasingly concerned about their algorithms causing major financial or reputational damage. High-profile cases include Google’s AI algorithm for photo classification mistakenly labelling a black couple as gorillas in 2015 (Gebru 2020 In The Oxford handbook of ethics of AI , pp. 251–269), Microsoft’s AI chatbot Tay that spread racist, sexist and antisemitic speech on Twitter (now X) (Wolf et al . 2017 ACM Sigcas Comput. Soc . 47 , 54–64 (doi: 10.1145/3144592.3144598 )), and Amazon’s AI recruiting tool being scrapped after showing bias against women. In response, governments are legislating and imposing bans, regulators fining companies and the judiciary discussing potentially making algorithms artificial ‘persons’ in law. As with financial audits, governments, business and society will require algorithm audits; formal assurance that algorithms are legal, ethical and safe. A new industry is envisaged: Auditing and Assurance of Algorithms (cf. data privacy), with the remit to professionalize and industrialize AI, ML and associated algorithms. The stakeholders range from those working on policy/regulation to industry practitioners and developers. We also anticipate the nature and scope of the auditing levels and framework presented will inform those interested in systems of governance and compliance with regulation/standards. Our goal in this article is to survey the key areas necessary to perform auditing and assurance and instigate the debate in this novel area of research and practice.
- 15 May 2024
- Published by The Royal Society in Royal Society Open Science
- Vol. 11 (5) , 230859
Top Cited PapersOpen AccessTowards algorithm auditing: managing legal, ethical and technological risks of AI, ML and associated algorithms
Business reliance on algorithms is becoming ubiquitous, and companies are increasingly concerned about their algorithms causing major financial or reputational damage. High-profile cases include Google’s AI algorithm for photo classification mistakenly labelling a black couple as gorillas in 2015 (Gebru 2020 In The Oxford handbook of ethics of AI , pp. 251–269), Microsoft’s AI chatbot Tay that spread racist, sexist and antisemitic speech on Twitter (now X) (Wolf et al . 2017 ACM Sigcas Comput. Soc . 47 , 54–64 (doi: 10.1145/3144592.3144598 )), and Amazon’s AI recruiting tool being scrapped after showing bias against women. In response, governments are legislating and imposing bans, regulators fining companies and the judiciary discussing potentially making algorithms artificial ‘persons’ in law. As with financial audits, governments, business and society will require algorithm audits; formal assurance that algorithms are legal, ethical and safe. A new industry is envisaged: Auditing and Assurance of Algorithms (cf. data privacy), with the remit to professionalize and industrialize AI, ML and associated algorithms. The stakeholders range from those working on policy/regulation to industry practitioners and developers. We also anticipate the nature and scope of the auditing levels and framework presented will inform those interested in systems of governance and compliance with regulation/standards. Our goal in this article is to survey the key areas necessary to perform auditing and assurance and instigate the debate in this novel area of research and practice.
- Open Access
SatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery
Geographic information is essential for modeling tasks in fields ranging from ecology to epidemiology. However, extracting relevant location characteristics for a given task can be challenging, often requiring expensive data fusion or distillation from massive global imagery datasets. To address this challenge, we introduce Satellite Contrastive Location-Image Pretraining (SatCLIP). This global, general-purpose geographic location encoder learns an implicit representation of locations by matching CNN and ViT inferred visual patterns of openly available satellite imagery with their geographic coordinates. The resulting SatCLIP location encoder efficiently summarizes the characteristics of any given location for convenient use in downstream tasks. In our experiments, we use SatCLIP embeddings to improve prediction performance on nine diverse location-dependent tasks including temperature prediction, animal recognition, and population density estimation. Across tasks, SatCLIP consistently outperforms alternative location encoders and improves geographic generalization by encoding visual similarities of spatially distant environments. These results demonstrate the potential of vision-location models to learn meaningful representations of our planet from the vast, varied, and largely untapped modalities of geospatial data.
Open AccessSatCLIP: Global, General-Purpose Location Embeddings with Satellite Imagery
Geographic information is essential for modeling tasks in fields ranging from ecology to epidemiology. However, extracting relevant location characteristics for a given task can be challenging, often requiring expensive data fusion or distillation from massive global imagery datasets. To address this challenge, we introduce Satellite Contrastive Location-Image Pretraining (SatCLIP). This global, general-purpose geographic location encoder learns an implicit representation of locations by matching CNN and ViT inferred visual patterns of openly available satellite imagery with their geographic coordinates. The resulting SatCLIP location encoder efficiently summarizes the characteristics of any given location for convenient use in downstream tasks. In our experiments, we use SatCLIP embeddings to improve prediction performance on nine diverse location-dependent tasks including temperature prediction, animal recognition, and population density estimation. Across tasks, SatCLIP consistently outperforms alternative location encoders and improves geographic generalization by encoding visual similarities of spatially distant environments. These results demonstrate the potential of vision-location models to learn meaningful representations of our planet from the vast, varied, and largely untapped modalities of geospatial data.
- 16 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 23 (3) , 2549-2560
Deployment Optimization for Shared e-Mobility Systems With Multi-Agent Deep Neural Search
Shared e-mobility services have been widely tested and piloted in cities across the globe, and already woven into the fabric of modern urban planning. This paper studies a practical yet important problem in those systems: how to deploy and manage their infrastructure across space and time, so that the services are ubiquitous to the users while sustainable in profitability. However, in real-world systems evaluating the performance of different deployment strategies and then finding the optimal plan is prohibitively expensive, as it is often infeasible to conduct many iterations of trial-and-error. We tackle this by designing a high-fidelity simulation environment, which abstracts the key operation details of the shared e-mobility systems at fine-granularity, and is calibrated using data collected from the real-world. This allows us to try out arbitrary deployment plans to learn the optimal given specific context, before actually implementing any in the real-world systems. In particular, we propose a novel multi-agent neural search approach, in which we design a hierarchical controller to produce tentative deployment plans. The generated deployment plans are then tested using a multi-simulation paradigm, i.e., evaluated in parallel, where the results are used to train the controller with deep reinforcement learning. With this closed loop, the controller can be steered to have higher probability of generating better deployment plans in future iterations. The proposed approach has been evaluated extensively in our simulation environment, and experimental results show that it outperforms baselines e.g., human knowledge, and state-of-the-art heuristic-based optimization approaches in both service coverage and net revenue.
- 16 November 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 23 (3) , 2549-2560
Deployment Optimization for Shared e-Mobility Systems With Multi-Agent Deep Neural Search
Shared e-mobility services have been widely tested and piloted in cities across the globe, and already woven into the fabric of modern urban planning. This paper studies a practical yet important problem in those systems: how to deploy and manage their infrastructure across space and time, so that the services are ubiquitous to the users while sustainable in profitability. However, in real-world systems evaluating the performance of different deployment strategies and then finding the optimal plan is prohibitively expensive, as it is often infeasible to conduct many iterations of trial-and-error. We tackle this by designing a high-fidelity simulation environment, which abstracts the key operation details of the shared e-mobility systems at fine-granularity, and is calibrated using data collected from the real-world. This allows us to try out arbitrary deployment plans to learn the optimal given specific context, before actually implementing any in the real-world systems. In particular, we propose a novel multi-agent neural search approach, in which we design a hierarchical controller to produce tentative deployment plans. The generated deployment plans are then tested using a multi-simulation paradigm, i.e., evaluated in parallel, where the results are used to train the controller with deep reinforcement learning. With this closed loop, the controller can be steered to have higher probability of generating better deployment plans in future iterations. The proposed approach has been evaluated extensively in our simulation environment, and experimental results show that it outperforms baselines e.g., human knowledge, and state-of-the-art heuristic-based optimization approaches in both service coverage and net revenue.
- Open Access
Auxiliary-task learning for geographic data with autoregressive embeddings
Machine learning is gaining popularity in a broad range of areas working with geographic data, such as ecology or atmospheric sciences. Here, data often exhibit spatial effects, which can be difficult to learn for neural networks. In this study, we propose SXL, a method for embedding information on the autoregressive nature of spatial data directly into the learning process using auxiliary tasks. We utilize the local Moran's I, a popular measure of local spatial autocorrelation, to "nudge" the model to learn the direction and magnitude of local spatial effects, complementing the learning of the primary task. We further introduce a novel expansion of Moran's I to multiple resolutions, thus capturing spatial interactions over longer and shorter distances simultaneously. The novel multi-resolution Moran's I can be constructed easily and as a multi-dimensional tensor offers seamless integration into existing machine learning frameworks. Throughout a range of experiments using real-world data, we highlight how our method consistently improves the training of neural networks in unsupervised and supervised learning tasks. In generative spatial modeling experiments, we propose a novel loss for auxiliary task GANs utilizing task uncertainty weights. Our proposed method outperforms domain-specific spatial interpolation benchmarks, highlighting its potential for downstream applications. This study bridges expertise from geographic information science and machine learning, showing how this integration of disciplines can help to address domain-specific challenges. The code for our experiments is available on Github: https://github.com/konstantinklemmer/sxl.
Open AccessAuxiliary-task learning for geographic data with autoregressive embeddings
Machine learning is gaining popularity in a broad range of areas working with geographic data, such as ecology or atmospheric sciences. Here, data often exhibit spatial effects, which can be difficult to learn for neural networks. In this study, we propose SXL, a method for embedding information on the autoregressive nature of spatial data directly into the learning process using auxiliary tasks. We utilize the local Moran's I, a popular measure of local spatial autocorrelation, to "nudge" the model to learn the direction and magnitude of local spatial effects, complementing the learning of the primary task. We further introduce a novel expansion of Moran's I to multiple resolutions, thus capturing spatial interactions over longer and shorter distances simultaneously. The novel multi-resolution Moran's I can be constructed easily and as a multi-dimensional tensor offers seamless integration into existing machine learning frameworks. Throughout a range of experiments using real-world data, we highlight how our method consistently improves the training of neural networks in unsupervised and supervised learning tasks. In generative spatial modeling experiments, we propose a novel loss for auxiliary task GANs utilizing task uncertainty weights. Our proposed method outperforms domain-specific spatial interpolation benchmarks, highlighting its potential for downstream applications. This study bridges expertise from geographic information science and machine learning, showing how this integration of disciplines can help to address domain-specific challenges. The code for our experiments is available on Github: https://github.com/konstantinklemmer/sxl.
- Open Access
- 10 February 2021
- Published by The Royal Society in Royal Society Open Science
- Vol. 8 (2)
Understanding spatial patterns in rape reporting delays
Under-reporting and delayed reporting of rape crime are severe issues that can complicate the prosecution of perpetrators and prevent rape survivors from receiving needed support. Building on a massive database of publicly available criminal reports from two US cities, we develop a machine learning framework to predict delayed reporting of rape to help tackle this issue. Motivated by large and unexplained spatial variation in reporting delays, we build predictive models to analyse spatial, temporal and socio-economic factors that might explain this variation. Our findings suggest that we can explain a substantial proportion of the variation in rape reporting delays using only openly available data. The insights from this study can be used to motivate targeted, data-driven policies to assist vulnerable communities. For example, we find that younger rape survivors and crimes committed during holiday seasons exhibit longer delays. Our insights can thus help organizations focused on supporting survivors of sexual violence to provide their services at the right place and time. Due to the non-confidential nature of the data used in our models, even community organizations lacking access to sensitive police data can use these findings to optimize their operations.
- 10 February 2021
- Published by The Royal Society in Royal Society Open Science
- Vol. 8 (2)
Open AccessUnderstanding spatial patterns in rape reporting delays
Under-reporting and delayed reporting of rape crime are severe issues that can complicate the prosecution of perpetrators and prevent rape survivors from receiving needed support. Building on a massive database of publicly available criminal reports from two US cities, we develop a machine learning framework to predict delayed reporting of rape to help tackle this issue. Motivated by large and unexplained spatial variation in reporting delays, we build predictive models to analyse spatial, temporal and socio-economic factors that might explain this variation. Our findings suggest that we can explain a substantial proportion of the variation in rape reporting delays using only openly available data. The insights from this study can be used to motivate targeted, data-driven policies to assist vulnerable communities. For example, we find that younger rape survivors and crimes committed during holiday seasons exhibit longer delays. Our insights can thus help organizations focused on supporting survivors of sexual violence to provide their services at the right place and time. Due to the non-confidential nature of the data used in our models, even community organizations lacking access to sensitive police data can use these findings to optimize their operations.
- Open Access
- 18 March 2020
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 4 (1) , 1-21
D3P
The future of urban mobility is expected to be shared and electric. It is not only a more sustainable paradigm that can reduce emissions, but can also bring societal benefits by offering a more affordable on-demand mobility option to the general public. Many car sharing service providers as well as automobile manufacturers are entering the competition by expanding both their EV fleets and renting/returning station networks, aiming to seize a share of the market and to bring car sharing to the zero emissions level. During their fast expansion, one determinant for success is the ability of predicting the demand of stations as the entire system is growing continuously. There are several challenges in this demand prediction problem: First, unlike most of the existing work which predicts demand only for static systems or at few stages of expansion, in the real world we often need to predict the demand as or even before stations are being deployed or closed, to provide information and decision support. Second, for the new stations to be deployed, there is no historical data available to help the prediction of their demand. Finally, the impact of deploying/closing stations on the other stations in the system can be complex. To address these challenges, we formulate the demand prediction problem in the context of fast expanding electric vehicle sharing systems, and propose a data-driven demand prediction approach which aims to model the expansion dynamics directly from the data. We use a local temporal encoding process to handle the historical data for each existing station, and a dynamic spatial encoding process to take correlations between stations into account with Graph Convolutional Neural Networks (GCN). The encoded features are fed to a multi-scale predictor, which forecasts both the long-term expected demand of the stations and their instant demand in the near future. We evaluate the proposed approach with real-world data collected from a major EV sharing platform for one year. Experimental results demonstrate that our approach significantly outperforms the state of the art, showing up to three-fold performance gain in predicting demand for the expanding EV sharing systems.
- 18 March 2020
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
- Vol. 4 (1) , 1-21
Open AccessD3P
The future of urban mobility is expected to be shared and electric. It is not only a more sustainable paradigm that can reduce emissions, but can also bring societal benefits by offering a more affordable on-demand mobility option to the general public. Many car sharing service providers as well as automobile manufacturers are entering the competition by expanding both their EV fleets and renting/returning station networks, aiming to seize a share of the market and to bring car sharing to the zero emissions level. During their fast expansion, one determinant for success is the ability of predicting the demand of stations as the entire system is growing continuously. There are several challenges in this demand prediction problem: First, unlike most of the existing work which predicts demand only for static systems or at few stages of expansion, in the real world we often need to predict the demand as or even before stations are being deployed or closed, to provide information and decision support. Second, for the new stations to be deployed, there is no historical data available to help the prediction of their demand. Finally, the impact of deploying/closing stations on the other stations in the system can be complex. To address these challenges, we formulate the demand prediction problem in the context of fast expanding electric vehicle sharing systems, and propose a data-driven demand prediction approach which aims to model the expansion dynamics directly from the data. We use a local temporal encoding process to handle the historical data for each existing station, and a dynamic spatial encoding process to take correlations between stations into account with Graph Convolutional Neural Networks (GCN). The encoded features are fed to a multi-scale predictor, which forecasts both the long-term expected demand of the stations and their instant demand in the near future. We evaluate the proposed approach with real-world data collected from a major EV sharing platform for one year. Experimental results demonstrate that our approach significantly outperforms the state of the art, showing up to three-fold performance gain in predicting demand for the expanding EV sharing systems.
- Open Access
Demand Prediction for Electric Vehicle Sharing
Electric Vehicle (EV) sharing systems have recently experienced unprecedented growth across the globe. Many car sharing service providers as well as automobile manufacturers are entering this competition by expanding both their EV fleets and renting/returning station networks, aiming to seize a share of the market and bring car sharing to the zero emissions level. During their fast expansion, one fundamental determinant for success is the capability of dynamically predicting the demand of stations. In this paper we propose a novel demand prediction approach, which is able to model the dynamics of the system and predict demand accordingly. We use a local temporal encoding process to handle the available historical data at individual stations, and a spatial encoding process to take correlations between stations into account with graph convolutional neural networks. The encoded features are fed to a prediction network, which forecasts both the long-term expected demand of the stations. We evaluate the proposed approach on real-world data collected from a major EV sharing platform. Experimental results demonstrate that our approach significantly outperforms the state of the art.
Open AccessDemand Prediction for Electric Vehicle Sharing
Electric Vehicle (EV) sharing systems have recently experienced unprecedented growth across the globe. Many car sharing service providers as well as automobile manufacturers are entering this competition by expanding both their EV fleets and renting/returning station networks, aiming to seize a share of the market and bring car sharing to the zero emissions level. During their fast expansion, one fundamental determinant for success is the capability of dynamically predicting the demand of stations. In this paper we propose a novel demand prediction approach, which is able to model the dynamics of the system and predict demand accordingly. We use a local temporal encoding process to handle the available historical data at individual stations, and a spatial encoding process to take correlations between stations into account with graph convolutional neural networks. The encoded features are fed to a prediction network, which forecasts both the long-term expected demand of the stations. We evaluate the proposed approach on real-world data collected from a major EV sharing platform. Experimental results demonstrate that our approach significantly outperforms the state of the art.
- Open Access
- 20 December 2018
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 13 (12) , e0209090
Isolating the effect of cycling on local business environments in London
We investigate whether increasing cycling activity affects the emergence of new local businesses. Historical amenity data from OpenStreetMap is used to quantify change in shop and sustenance amenity counts. We apply an instrumental variable framework to investigate a causal relationship and to account for endogeneity in the model. Measures of cycling infrastructure serve as instruments. The impact is evaluated on the level of 4835 Lower Super Output Areas in Greater London. Our results indicate that an increase in cycling trips significantly contributes to the emergence of new local shops and businesses. Limitations regarding data quality, zero-inflation and residual spatial autocorrelation are discussed. While our findings correspond to previous investigations stating positive economic effects of cycling, we advance research in the field by providing a new dataset of unprecedented high granularity and size. Furthermore, this is the first study in cycling research looking at business amenities as a measure of economic activity. The insights from our analysis can enhance understandings of how cycling affects the development of local urban economies and may thus be used to assess and evaluate transport policies and investments. Beyond this, our study highlights the value of open data in city research.
- 20 December 2018
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 13 (12) , e0209090
Open AccessIsolating the effect of cycling on local business environments in London
We investigate whether increasing cycling activity affects the emergence of new local businesses. Historical amenity data from OpenStreetMap is used to quantify change in shop and sustenance amenity counts. We apply an instrumental variable framework to investigate a causal relationship and to account for endogeneity in the model. Measures of cycling infrastructure serve as instruments. The impact is evaluated on the level of 4835 Lower Super Output Areas in Greater London. Our results indicate that an increase in cycling trips significantly contributes to the emergence of new local shops and businesses. Limitations regarding data quality, zero-inflation and residual spatial autocorrelation are discussed. While our findings correspond to previous investigations stating positive economic effects of cycling, we advance research in the field by providing a new dataset of unprecedented high granularity and size. Furthermore, this is the first study in cycling research looking at business amenities as a measure of economic activity. The insights from our analysis can enhance understandings of how cycling affects the development of local urban economies and may thus be used to assess and evaluate transport policies and investments. Beyond this, our study highlights the value of open data in city research.