Minimizing Commute Time Impact

This is the kind of research we need more of: Dutch Railways (NS) delivers 11x more value to society than it costs, yet we still call it a ‘loss-maker’. Some key facts before I go into this: ▶ NS lost €141 million financially in 2024 ▶ But created €1.33 billion in societal value ▶ NS (Nederlandse Spoorwegen) is the national railway company of the Netherlands — and it’s 100% government-owned ▶ Its trains run entirely on renewable wind energy ▶ The government still spends €37.5 billion per year subsidising fossil fuels ▶ Dutch roads are more congested than ever Now, new research by Professor Dirk Schoenmaker (Erasmus University) and Wander Marijnissen (ftrprf) reveals something remarkable: In 2024, NS recorded a financial loss of €141 million — but generated €1.33 billion in social value. 🏛 Financial loss ≠ societal failure The study shows that NS creates massive value through social inclusion, accessibility, property value growth, employee welfare, and low-carbon transport, while also accounting for negatives like delays and noise pollution. Their conclusion: the social return of NS is 11.3 times higher than its financial performance (!). When governments or media reduce this to a “loss,” they’re looking at the simplest of financial calculations, only considering the direct financial value generated from operating the train network. They ignore what really matters: how public transport gives people economic and social access to different parts of the country, reduces inequality, and lowers emissions. 🚉 Public transport is a public investment Chronic underfunding leads to higher fares, worse service, and declining accessibility. We can’t keep calling something a cost when it never should have been a capitalistic profit driver in the first place. 🌍 The bigger picture The same researchers found that car traffic costs society twice as much per kilometre as train delays, yet policy and pricing still favour cars. Meanwhile, NS trains already run on 100% wind power, offering a blueprint for climate-friendly transport systems worldwide. This type of research is really good at highlighting that the financial lens often overlooks the real benefits to society. Looking forward to reading more papers like this.

This is a fantastic example of modern geospatial analytics in action. A new paper from Andreas Christen and the team at the University of Freiburg demonstrates how AI can help cities balance two competing goals: urban densification and heat mitigation. The real power here lies in the orchestration of multiple complex datasets to drive actionable insights. The study didn't just map temperature; it fused LiDAR point clouds, 3D semantic city models, and historical weather data into a unified AI workflow. Instead of traditional, computationally expensive physical simulations, they used AI models to rapidly predict "thermal comfort" at a hyper-local scale. This allows for: - Data Fusion: distinct datasets (geometry, vegetation, climate) working together. - Prescriptive Analytics: Moving beyond descriptive maps to automated optimization identifying exactly where to plant trees or place buildings for maximum cooling. It’s a glimpse into the future of urban planning, where geospatial data and AI doesn't just describe the problem, but actively designs the solution. Congrats to the team and great paper/read! Read the paper here: https://lnkd.in/eqBCym9Z 🌎 I'm Matt Forrest and I talk about modern GIS, earth observation, AI, and how geospatial is changing. 📬 Want more like this? Join 12k+ others learning from my daily newsletter → forrest.nyc

Your GIS maps don't talk to your BIM. Your traffic sensors (IoT) don't inform your emergency response. Your drone footage is just ... sitting on a drive. A City Information Model (CIM) fixes this. I've attached the exact framework that successful smart cities like Helsinki and Singapore use. It's not about more data. It's about connecting the data you already have. Here's the simple, 3-stage breakdown 👇 Stage 1: Data Acquisition This is about cataloguing what you already own. - Geographic Info (GIS): Your maps, roads, and utility lines. - Building Info (BIM): 3D models of new and existing structures. - Sensors (IoT): Traffic, air quality, waste management. - Remote Sensing: Drone and satellite imagery. Right now, these are all in separate "drawers." The goal is to bring them to the same "table." Stage 2: Data Processing This is the most critical step. It’s where you break the silos. - Clean & Standardize: Make all data speak the same language using standards like ISO/OGC. - Fuse & Integrate: This is where GIS + BIM + IoT data are merged. Your 3D building model now "knows" its location on the map and its real-time energy use. - Analyze: Use AI to mine patterns. For example: "This intersection always floods when rainfall exceeds 2 inches, and traffic backs up 3 miles. Let's re-route automatically next time."🖐️ Stage 3: Data Application This is why you did the work. Your connected data is now a tool. You can now finally, visualize (meaningful) in 3D. - Optimize Emergency: Deploy first responders with pinpoint accuracy. - Monitor Environment: Track air quality, noise pollution, or energy use. I've attached this framework for you to consider. --------- Follow me for #digitaltwins Links in my profile Florian Huemer

In Singapore, advanced urban infrastructure is tackling the growing challenge of flash floods with the introduction of smart drains. These drainage systems are equipped with sensors that monitor rainfall intensity, water levels, and flow rates in real time. When heavy rain is detected, the smart drains automatically open their gates or adjust flow channels to direct excess water away from vulnerable areas, reducing the risk of urban flooding. The system is linked to a central control network, allowing authorities to respond instantly to changing weather conditions. In some cases, the drains can work in coordination with detention tanks and flood barriers, creating a layered defense against sudden downpours. This automation not only protects streets and properties but also minimizes disruption to traffic and public services. Singapore’s approach reflects its forward-thinking urban planning, where technology and sustainability go hand in hand. By preventing water from accumulating in low-lying areas, the smart drains help protect both infrastructure and the daily lives of residents. As climate change increases the frequency of extreme weather events, such innovations could serve as a model for other flood-prone cities worldwide.

Many think that low-density areas can’t support public transport. But Helsinki has another approach. The secret? Buses. 🚇 Helsinki operates a single metro line extending into distant suburbs, yet the line serves over 300,000 riders daily thanks to the bus. 🚍 For example, Espoo's western suburb now has a robust network of feeder buses. Helsinki’s buses provide frequent, reliable service that feeds into metro stations. ⏳ These buses run every 5-10 minutes (!), drastically reducing wait times and making public transport a viable alternative to driving. 🏢 Great transit allows Espoo to grow and densify, which will support all this investment in the future. Paul Mees put it perfectly: "Arguments that [higher] densities are needed before transport trends can change are really just arguments for continuing with automobile dependence." Helsinki’s approach to public transport shows that even suburban areas with low population density can achieve high levels of public transit usage. Link to the great video by George Liu PhD and Jedwin Mok on EIT Urban Mobility - Urban Mobility Explained (UMX) in the comments. Featuring Jonathan English.

In public transport, frequency is king. Brampton, Ontario, a Canadian low-density suburb might have some of the densest transit usage - in North America, where cars have been the dominant force for a century. - 226,000 daily ridership, out of a population of ~700,000 - that’s 1/3rd of the population! - 4x growth from 2004 to 2018 - with relatively low public subsidy, compared to peers. How did they do it? Not by building an expensive metro, but by using the humble bus. It’s a simple playbook - provide predictable, frequent services and the users will come. A 54% increase in Sunday services led to a 177% increase in ridership, simply by providing consistency and frequency. Brampton didn’t build demand-responsive transit - they 𝘪𝘯𝘥𝘶𝘤𝘦𝘥 demand using transit. This could be the model of success for a lot of cities in India - possibly better than expensive metros that take years to build. India needs more buses - low investment, high impact. https://lnkd.in/dAzztZ3f

As gasoline prices rise, commuters are encouraged to take public transit and work from home if possible, but the transition isn’t that easy. The U.S. Census Bureau’s 2024 ACS data indicate that 13% of all workers in the US worked remotely. Among commuters, 90% drove a personal vehicle or carpooled to work, and just 4% used public transportation. Just 6 of 199 metro areas with a population of at least 250K had at least 1 in 10 commuters relying on public transportation in 2024. The median share of public transit reliance across the major metro areas was a measly 0.9%. Cities with higher population density and legacy public transit infrastructure tend to see higher usage. The New York-Newark-Jersey City metro area was at the top with 31% of its commuters using public transportation, followed by San Francisco-Oakland-Fremont (13%) and Boston-Cambridge-Newton (12%). Within NYC’s 5 boroughs, 56% of commuters used public transportation, well above the national share. Many commuters have no choice but to drive. Some communities aren’t connected to any mass transit. Poor design choices and service quality further discourage the use of public transit. That partly explains why transportation habits usually don’t change much as gas prices fluctuate. But it doesn’t have to be this way. Long-term investment in public transit infrastructure can give commuters more options to mitigate the impact of changing gas prices.  #gasoline #transit

Here's a surprising reality: while a significant majority, around 25%, of organizational data possesses a geospatial element, it's estimated that less than 2% of businesses are truly capitalizing on its potential for deeper understanding. 🤯 Ever feel like you're navigating your business decisions with a blurry map? 🗺️ You're not alone in dealing with the challenge of location data. 𝐓𝐡𝐞 𝐫𝐞𝐚𝐥 𝐩𝐫𝐨𝐛𝐥𝐞𝐦: 👉 The core issue lies in the complexities often associated with harnessing location data. For many organizations, extracting meaningful insights from geographically referenced information can be a significant hurdle. 👉 Siloed systems, data format inconsistencies, and the sheer scale of geospatial datasets often make comprehensive analysis a time-consuming and resource-intensive process. This can prevent businesses from effectively understanding spatial relationships in customer behavior, logistical efficiencies, or risk distributions. 😫 𝐓𝐡𝐞 𝐬𝐨𝐥𝐮𝐭𝐢𝐨𝐧: However, progress is being made in making this valuable data more accessible and actionable. A recent blog post from Google Cloud highlights how CNA, a prominent insurance provider, is addressing this challenge by leveraging BigQuery for its geospatial analytics needs. 🚀 By centralizing their diverse location data within BigQuery and utilizing its specialized geospatial capabilities, CNA has been able to streamline complex analyses and gain new perspectives. This allows them to visualize geographical patterns in risk, optimize resource allocation based on location intelligence, and develop a more nuanced understanding of their customers through a spatial lens – all within a scalable and efficient data environment. ✨ 𝐖𝐡𝐚𝐭 𝐝𝐨𝐞𝐬 𝐭𝐡𝐢𝐬 𝐭𝐫𝐞𝐧𝐝 𝐦𝐞𝐚𝐧 𝐟𝐨𝐫 𝐨𝐫𝐠𝐚𝐧𝐢𝐳𝐚𝐭𝐢𝐨𝐧𝐬 𝐢𝐧 𝐠𝐞𝐧𝐞𝐫𝐚𝐥? 𝐓𝐡𝐞 𝐩𝐨𝐭𝐞𝐧𝐭𝐢𝐚𝐥 𝐛𝐞𝐧𝐞𝐟𝐢𝐭𝐬 𝐚𝐫𝐞 𝐬𝐮𝐛𝐬𝐭𝐚𝐧𝐭𝐢𝐚𝐥: 👉 More Informed Decision-Making: Accessing location-aware insights can lead to more strategic and operationally sound choices. 🧠 👉 Identification of Opportunities: Uncovering previously unseen market segments and tailoring offerings based on geographic context can unlock new potential. 💰 👉 Deeper Customer Understanding: Gaining insights into customer behavior, preferences, and needs based on their location can lead to better engagement. 📍 👉 Increased Responsiveness: The ability to quickly analyze spatial patterns allows for more agile responses to changing conditions. 💨 Ultimately, the evolution of data warehousing platforms to seamlessly integrate advanced geospatial analytics represents a significant step forward. It moves location intelligence from a specialized domain to a more accessible and integral part of organizational analysis. Follow Omkar Sawant for more. #GeospatialAnalysis #Data #Insights #Cloud #Analytics #Trends #BusinessIntelligence

🏙️ Urban Planning is Changing — GeoAI + High-Resolution Data is Leading the Shift Traditional urban planning relied on surveys, static maps, and outdated census layers. Today? We can model cities in near real-time using GeoAI + high-resolution satellite & spatial data. Here’s how modern urban intelligence works 👇 🔍 1. High-Resolution Satellite Imagery (≤1m) Detect informal settlements, building footprints, road encroachments, and land-use change with precision. 📊 2. AI-Based Urban Growth Modeling Predict expansion corridors before uncontrolled sprawl happens. 🌡️ 3. Urban Heat & Microclimate Mapping Integrate LST + building density + vegetation indices to design climate-resilient cities. 🚦 4. Traffic & Mobility Optimization Use spatial ML to identify congestion hotspots and optimize infrastructure planning. 🌊 5. Flood & Drainage Simulation Combine high-resolution DEM + rainfall + impervious surface mapping to prevent urban flooding. 🌳 6. Green Space & Carbon Planning Quantify urban canopy, carbon storage, and environmental equity gaps. The difference today is resolution + intelligence. Not just better pixels — smarter models. Cities that use GeoAI are moving from reactive planning to predictive governance. If you’re working on: • Smart city development • Climate-resilient urban design • Urban growth modeling • Infrastructure risk assessment Let’s collaborate on high-resolution GeoAI workflows that turn spatial data into planning decisions. The future of cities is spatial. And intelligent. #UrbanPlanning #GeoAI #GIS #SmartCities #SpatialDataScience #RemoteSensing #UrbanAnalytics #ClimateResilience #HighResolutionData #SpatialML #CityPlanning #EarthObservation #Geospatial

What if Telcos built the next foundation model for the physical world? LLMs are trained on language. But cities don’t speak in words, they speak in patterns. The way people move, where networks strain, how demand surges and infrastructure reacts; these are dynamic, physical signals. They can’t be scraped from the web or inferred from text. They can only be seen through infrastructure that exists in the physical world. Telcos have this vantage point. They generate one of the richest, most continuous, and anonymized data streams about how cities truly operate. From handover patterns to network congestion, from app usage to device density, Telcos hold a live, multimodal view of urban behavior at scale. This isn’t just metadata, but a window into the pulse of real-time human activity. In my latest research, I introduce SmartCityFM: a foundation model built not from documents, but from telecom infrastructure data. It captures spatiotemporal intelligence, or the ability to reason about how cities function over time, across space, and under different stress conditions. SmartCityFM is trained on mobility patterns, signal quality, behavioral trends, and contextual network signals using a transformer-based multimodal architecture and federated learning principles. This model enables real-world capabilities: forecasting urban flows, simulating the resilience of public infrastructure, guiding zoning and retail decisions, and powering AI copilots for governments and transport planners. More importantly, it unlocks a monetization path for Telcos through APIs, predictive services, and real-time intelligence layers for cities, real estate, logistics, and more. It’s a new class of AI. One that is grounded in the physical world. One that Telcos are uniquely positioned to build. You can read the full paper here: https://lnkd.in/dxm-uKpE This is part of my 12-part series on Telco AI monetization. Previous editions are available here: https://lnkd.in/dEFh2V3G https://lnkd.in/dezHkw_X