Levi Szamek

Hi im Levi,
I did my Msc. in Geoinformatics at the University of Heidelberg, Germany. Already during my time as a student I worked at HeiGIT on open-source applications from and for OSM. Since 2025 I have been working at HeiGIT as a developer and researcher at the intersection of geographic information science and humanitarian applications, contributing to free, open-source geoinformation systems for environmental and societal benefit. The focus of my work is on quality assessments of OSM data. In recent years, my research focus has shifted to deep-learning solutions for solid waste detection.


Sessions

11-28
14:20
20min
Adaptive Humanitarian Mobility: Dynamic OSM-Based Routing with Critical Mission Data
Julian Psotta, Levi Szamek

In humanitarian crises, rapidly changing conditions such as damaged infrastructure, weather hazards, or security threats significantly impact the efficiency and safety of aid delivery and logistics. Standard static routing methods, even those leveraging regularly updated OpenStreetMap (OSM) data, often fail to quickly adapt when a critical bridge collapses overnight or a newly flooded road blocks previously safe routes. Thus, lacking the flexibility to integrate rapidly evolving, mission-critical information from humanitarian organizations and local communities. Our approach addresses this gap by dynamically incorporating real-time, external operational data directly into mobility analysis.

OpenStreetMap provides a foundational role in disaster response, empowering local and remote volunteers to rapidly update map features like road accessibility, infrastructure status, and community resources. Active OSM mapping efforts, such as those coordinated by the Humanitarian OpenStreetMap Team (HOT), continuously enhance the accuracy and timeliness of geographic information available to humanitarian responders. Community-led mapping initiatives ensure that routes, landmarks, and hazard areas are promptly updated, directly benefiting routing decisions during crisis operations.

In this talk, you will learn about multiple aspects:

  • How does your mapping in OSM directly influence humanitarian mobility analysis, and what can you do to enhance this during mapping.
  • How do we close the gap between OSM data, which is updated at a slower but steady pace during disasters, and the need for current mission-critical ground truth within the mobility analysis.

The approach we are exploring allows integrating additional critical information such as precise flood extents, infrastructure damage assessments, or security conditions provided by humanitarian responders, satellites, or other data sources. This closes the gap between steady OSM changes and information that may not be suitable for OSM or just too temporary. The unique strength of our system lies in incorporating these external data sources into routing decisions in near real time, significantly improving the relevance and timeliness of route planning. You will discover how our innovative streaming method updates routing graphs rapidly, maintaining high performance and dynamically adapting to changing conditions without the need to do time expensive routing graph rebuilds.

Implemented within the open-source Openrouteservice (ORS) platform, this solution leverages a robust API that can be publicly accessed or self-hosted, ensuring broad interoperability and no technology lock-in. The development is in preview and access is still provided for humanitarian actors on demand only. This allows us to slowly roll out this functionality by still providing enough resources specifically for crisis-affected areas.

The practical humanitarian benefits are substantial. During major disasters such as Cyclone Idai in Mozambique (2019), and the 2023 Turkey–Syria earthquakes, which destroyed critical infrastructure impacting access for millions, responders urgently required flexible routing reflecting rapidly changing ground realities. Our dynamic routing system enables humanitarian organizations to adapt quickly, improving response speed, safety, and efficiency, thus optimizing limited resources.

Looking forward, the integration of predictive analytics based on accumulated operational data can further enhance humanitarian logistics. Such advancements could proactively identify routes at risk, enabling a shift from reactive to anticipatory routing.
This talk presents the state-of-the-art integration of dynamic mission-critical data and active OSM mapping efforts into humanitarian routing, highlighting its current implementation, practical impact, and future potential for proactive, resilient humanitarian logistics.

Humanitarian
Auditorium
11-29
14:05
5min
New insights into global mapping with the updated ohsomeNow Stats
Levi Szamek

ohsomeNow (also referred to as ohsomeNow Stats) is a real-time analytics dashboard and API developed by the Heidelberg Institute for Geoinformation Technology (HeiGIT). It tracks and visualizes OSM contributions globally. ohsomeNow brings transparency and context to OpenStreetMap’s massive, ongoing collaboration. Its fine-grained, flexible analytics help users understand mapping behavior patterns, measure impact of events or campaigns, and monitor trends at country or global levels.

The newly upgraded ohsomeNow Stats dashboard offers near real-time access to all OSM contributions since 2005, enabling detailed, flexible analysis of global mapping activities. Developed in partnership with the Humanitarian OpenStreetMap Team (HOT), it now includes all edits—not just those tagged with hashtags—updated every minute and calculated on demand.

Data analysis
Auditorium
11-30
14:00
30min
From street-view-imagery to actionable data: experiences from mapping waste in Dar es Salaam
Levi Szamek

Municipal solid waste (MSW) is a growing global challenge, with 3 billion people lacking access to safe disposal and global waste generation expected to rise from 2.01 to 3.40 billion tonnes by 2050. Poor waste management, especially open dumping, contributes to environmental degradation, disease transmission, and emerging health risks from microplastics. Despite the UN’s call to end unsafe waste practices, effective and inclusive management systems remain critically underdeveloped—particularly in Sub-Saharan Africa, where less than 50% of MSW is collected and about 70% is openly dumped. In East Africa, Tanzania—and especially its commercial capital, Dar es Salaam—stands out as a hotspot for mismanaged plastic waste. The city generates approximately 4,600 tonnes of waste daily, yet less than 40% is collected, with the remainder being illegaly burned or dumped to later accumulate in streets, drains, and rivers, including the heavily polluted Msimbazi River, a major contributor of plastic waste to the Indian Ocean.

To address the lack of reliable data on urban waste accumulation, we present a city-scale, open-data-based approach to map visible MSW in Dar es Salaam using deep learning and street-view imagery (SVI). In close collaboration with OpenMap Development Tanzania and HeiGIT, we developed an open-source end-to-end workflow that involves collecting, annotating, and processing 360-degree SVI across 41 wards, training a deep learning classification model to detect solid waste, and generating a high-resolution MSW pollution indicator. This approach provides actionable spatial insights to optimize urban cleaning strategies, reduce health risks linked to water contamination, and support evidence-based planning for more sustainable waste management.

The Street-view imagery was collected between throughout 2024 by OMDTZ using a Bajaj tricycle equipped with a GoPro Max 360° camera. This data collection effort covered major roads across Dar es Salaam. The imagery was made publicly available on Mapillary to enable open access and collaborative research.

To identify visible waste in street-view images, a two-step image annotation process was implemented using the open-source tool MapSwipe4Web for. Additionaly to manual labeling, we opted for Crowdsourced Pre-labeling: The MapSwipe community reviewed street-level panoramic images and flagged those containing visible waste. All positively labeled images were manually reviewed by the authors to ensure quality. Further manual labeling was conducted, particularly for underrepresented classes.

Images were annotated into the following three main classes: Waste Piles: Defined as accumulations of waste with horizontal and vertical extent, often indicative of illegal dumping or unmanaged MSW. Trash Bags: Properly packaged waste (typically in plastic or paper bags) that appears to be ready for collection. No Trash: Images with no visible waste.

To ensure spatial representativeness and reduce redundancy, images were sampled approximately every 10 meters along one-third of the road segments in each ward. In total, over 40,000 360° street-view panoramas were annotated. Due to the computational and geometric challenges associated with high-resolution equirectangular imagery, each panorama was segmented into 12 overlapping patches. This approach reduced computational load, minimized distortion effects, and maintained spatial context for classification. Further labelling on the image patches resulted in a final training dataset size of 7378 (with augmented 29605) waste images and 7640 (27410) no waste images for the trashbag model and 1818 (7325) waste images and 1920 (6965) no waste images for the waste model. A classification-based approach utilizing the YOLOv11 architecture was employed to detect visible waste, as it significantly reduces annotation effort by eliminating the need for bounding box labeling. This method was used because conventional object detection offers limited practical benefits and introduces unnecessary complexity to the annotation workflow.. The resulting models demonstrated strong performance, achieving precision scores of 0.87 for trash bags and 0.98 for waste piles, and recall scores of 0.86 and 0.98, respectively.

Nevertheless, some limitation need to be considered. For instance, the model occasionally struggled to distinguish between visually similar objects like trash bags and plastic buckets or plastic tarpaulins. For waste piles, materials like rubble or patterned floor mosaics sometimes led to misclassifications..

We deployed the trained models across the entire city, processing a total of 500,000 panoramic images covering 1300 kilometers of road network. The results were aggregated onto a hexagonal grid to produce a spatially explicit indicator of visible waste pollution. This analysis was further complemented with UAV-derived observations of waste piles along the Msimbazi River—a region largely inaccessible to ground-based street-view imaging—yielding a comprehensive waste pollution map for the entire study area.

Using this workflow we can show that there are several hotspots of waste pollution in Dar es Salaam mostly located in densly populated informal settlements, while the wards along the coastline show only little waste pollution. Combining the created data with data from OSM, it was recognised that there is a lot of open waste in the immediate vicinity of the drainage system, which can lead to a higher risk of flooding due to clogging.

Our results show the value of street view imagery for open mapping in OpenStreetMap and beyond. The extensive SVI of the entire street-network provides possibilities for other future usa-cases to enhance OSM like building material, blockage of drainage canals, road surface, etc.

The source data, code, and resulting datasets are publicly accessible, and the entire workflow is transferable to other geographic regions. The required resources are relatively low-cost, and open-source crowdsourcing tools, such as MapSwipe, can be leveraged to efficiently generate comprehensive datasets for model training.

Innovation
Audition Room - 1st Floor