# mapping Published articles for mapping. This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles. ## NASA and IBM open source lunar mapping tools DevFeed: [NASA and IBM open source lunar mapping tools]() Original publisher: [Read original article]() Author: Dan Robinson Published: 2026-09-10T16:09:12Z Content type: news Language: en Sources: [www.theregister.com - Articles]() Topics: [Open Source]() Tags: [ai-and-ml](), [artificial-intelligence](), [ibm](), [lunar-foundation-model](), [mapping](), [nasa](), [open-source]() ### AI overview NASA and IBM open-source lunar mapping tools intended to help identify locations on the Moon and support scientific discoveries. ### Source excerpt Can help you pick the perfect spot for your future evil lair, or boffins make discoveries about Earth's satellite ## Introducing IBM and NASA's new foundation model for the Moon DevFeed: [Introducing IBM and NASA's new foundation model for the Moon]() Original publisher: [Read original article]() Author: Kim Martineau Published: 2026-09-10T12:30:00Z Content type: article Language: en Sources: [IBM Research]() Topics: [lunar foundation model](), [ibm](), [foundation-models](), [data](), [Artificial Intelligence](), [AI Architecture]() Tags: [accelerated-discovery](), [ai](), [ai-architecture](), [algorithms](), [ibm](), [lunar-foundation-model](), [mapping](), [model](), [nasa](), [release](), [science](), [space](), [us]() ### AI overview IBM and NASA are open-sourcing the NASA-IBM Lunar Foundation Model, a multimodal AI model that integrates lunar observations from US and Japanese missions across viewing angles, spatial scales, and measurement types. The model is intended to support lunar mapping, volcanic-history research, and searches for polar ice. ### Source excerpt The multi-modal model could help astronauts navigate craters, investigate ancient lava, and search for ice, as the US plans for a long-term lunar presence. ## Threat matrix: Mapping threats across cloud web applications DevFeed: [Threat matrix: Mapping threats across cloud web applications]() Original publisher: [Read original article]() Author: Microsoft Security Research and Lior Leizerovich Published: 2026-09-09T21:30:00Z Content type: article Language: en Sources: [Microsoft Security Blog]() Topics: [web applications](), [cloud-infrastructure](), [Microsoft]() Tags: [cloud](), [framework](), [mapping](), [microsoft](), [security](), [serverless](), [web-applications]() ### AI overview Microsoft introduces a MITRE ATT&CK-aligned threat matrix for cloud-hosted web applications and serverless platforms. The framework maps attack techniques to help security teams identify visibility gaps, prioritize hardening, and investigate threats across application and cloud layers. ### Source excerpt Microsoft introduces the Cloud Web Applications Threat Matrix, a MITRE ATT&CK-aligned framework that helps defenders understand, prioritize, and mitigate threats to cloud-hosted web apps and serverless platforms. The post Threat matrix: Mapping threats across cloud web applications appeared first on Microsoft Security Blog. ## Beyond embedding: How to secure AI/BI Dashboards for every viewer DevFeed: [Beyond embedding: How to secure AI/BI Dashboards for every viewer]() Original publisher: [Read original article]() Author: Sonakshi Pandey Published: 2026-09-09T14:04:44Z Content type: tutorial Language: en Sources: [Databricks]() Topics: [databricks](), [Authorization](), [Grafana](), [SDKs](), [Back end](), [data]() Tags: [authorization](), [backend](), [dashboards](), [databricks](), [embedded](), [guide](), [idp](), [mapping](), [platform](), [product](), [sdk](), [sql]() ### AI overview This guide presents a Databricks design pattern for securing embedded AI/BI Dashboards for different viewers. It uses scoped embed tokens, __aibi_external_value, Unity Catalog row filters and column masks, and identity-provider-synchronized groups so one dashboard can show each viewer only the authorized regions and fields. The same entitlement table governs embedded dashboard access and direct Databricks SQL queries. ### Source excerpt The challengeEmbedding a Databricks AI/BI Dashboard in a customer-facing application is relatively straightforward... ## Mapping global methane emissions from space with deep learning DevFeed: [Mapping global methane emissions from space with deep learning]() Original publisher: [Read original article]() Published: 2026-09-01T18:40:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Deep neural networks](), [Google]() Tags: [climate-sustainability](), [deep-learning](), [earth-ai](), [framework](), [global](), [google](), [machine-intelligence](), [mapping](), [nasa](), [research](), [space]() ### AI overview The article presents MAPL-EMIT, a deep-learning framework for automating global detection, enhancement prediction, and source estimation of methane plumes from EMIT hyperspectral satellite measurements. ### Source excerpt Climate & Sustainability ## Planetary prediction engine: Automating global models via Earth AI DevFeed: [Planetary prediction engine: Automating global models via Earth AI]() Original publisher: [Read original article]() Published: 2026-08-27T17:37:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Earth AI](), [Artificial Intelligence](), [data-engineering](), [Google](), [Machine learning](), [AI Development](), [Feature Engineering](), [Model Development]() Tags: [agents](), [ai](), [analytics](), [data-engineering](), [earth-ai](), [evaluation](), [feature-engineering](), [generative-ai](), [google](), [insights](), [machine-intelligence](), [mapping](), [research](), [training](), [validation](), [workflow](), [workflows]() ### AI overview Google Research introduces the Planetary Prediction Engine, an experimental Earth AI capability that autonomously performs geospatial data discovery, cleanup, feature engineering, model training, evaluation, and report generation from natural-language queries. The system targets applications including public health, food security, environmental risk, and socioeconomic analysis, reducing the stated workflow from weeks of manual data engineering to minutes. ### Source excerpt Earth AI ## Generic Methods DevFeed: [Generic Methods]() Original publisher: [Read original article]() Author: Mark Freeman Published: 2026-08-26T00:00:00Z Content type: article Language: en Sources: [The Go Blog]() Topics: [Go Language](), [Go](), [Data structures](), [Sorting]() Tags: [feature](), [go](), [mapping](), [sorting](), [types]() ### AI overview Go 1.27 introduces generic methods, extending Go's type-parameter capabilities from generic types and functions to methods. The article explains the design rationale and shows how generic methods improve organization, local scoping, and readability for operations such as transforming linked-list values. ### Source excerpt Go 1.27 adds generic methods--a highly desired language feature. ## Online index migration and shard scaling in OpenSearch with the AOSC plugin DevFeed: [Online index migration and shard scaling in OpenSearch with the AOSC plugin]() Original publisher: [Read original article]() Author: Arpit Singla Published: 2026-08-18T21:56:28Z Content type: article Language: en Sources: [OpenSearch]() Topics: [Amazon OpenSearch Service](), [migration](), [Open Source](), [Routing (disambiguation)]() Tags: [blog](), [mapping](), [migration](), [open-source](), [opensearch](), [pipeline](), [plugin](), [production](), [reconciliation](), [routing](), [schema](), [technical](), [workflow]() ### AI overview This article introduces Automatic Online Schema Change (AOSC), an open-source OpenSearch plugin for migrating live indexes to pre-created targets with different mappings, settings, shard counts, or document shapes. It backfills existing documents, replays operations made during migration, and switches an alias after a short write block, while documenting its scaling behavior and limitations. ### Source excerpt Learn how the open-source AOSC plugin migrates live OpenSearch indexes--changing mappings, settings, or shard counts--without losing writes or requiring downtime. The post Online index migration and shard scaling in OpenSearch with the AOSC plugin appeared first on OpenSearch. ## What is a data topology? DevFeed: [What is a data topology?]() Original publisher: [Read original article]() Author: Ahmed Darwich Published: 2026-08-17T00:00:00Z Content type: article Language: en Sources: [Blog -- PlanetScale]() Topics: [data](), [vitess]() Tags: [architecture](), [data](), [database](), [engineering](), [internals](), [json](), [mapping](), [neki](), [performance](), [postgres](), [postgresql](), [routing](), [scalability](), [transactions](), [vitess]() ### AI overview The article explains Neki data topologies: JSON configurations that map logical PostgreSQL tables to physical shard groups so routers can place data and route queries. ### Source excerpt A data topology describes the sharding scheme a Neki router uses to map logical PostgreSQL tables to physical shards and route queries. ## When Escape Routes Become Toll Roads: Mapping How Developers Move Between Programming Languages DevFeed: [When Escape Routes Become Toll Roads: Mapping How Developers Move Between Programming Languages]() Original publisher: [Read original article]() Author: Vladimir Volokhonsky Published: 2026-08-12T16:15:18Z Content type: article Language: en Sources: [Kotlin : A concise multiplatform language developed by JetBrains | The JetBrains Blog]() Topics: [migration]() Tags: [articles-2](), [deveco](), [developers](), [kotlin](), [mapping](), [migration](), [programming](), [research]() ### AI overview A survey-based article on how developers move between programming languages. Project requirements are the main switching driver, while Kotlin stands out for its development experience and modern features. ### Source excerpt TL;DR: This post relates findings about language migration from the 2025 State of Developer Ecosystem survey. In general, project requirements are still the most common reasons for switching languages. One outlier from this trend, however, is Kotlin. People switch to Kotlin not because they have to; they switch because it simply feels better to work [...] ## Mapping the AI economy DevFeed: [Mapping the AI economy]() Original publisher: [Read original article]() Author: Abhi Tiwari Published: 2026-08-11T00:00:00Z Content type: article Language: en Sources: [Stripe Blog]() Topics: [Artificial Intelligence](), [stripe](), [data]() Tags: [ai](), [analysis](), [brazil](), [data](), [global](), [global-expansion](), [growth](), [india](), [japan](), [mapping](), [payment](), [stripe]() ### AI overview Stripe analyzes transaction data from AI companies to map global AI demand, identifying high-spend and high-momentum markets and highlighting localization strategies for international revenue growth. ### Source excerpt AI companies are undergoing rapid global expansion while achieving unprecedented rates of growth. We analyzed Stripe data to understand where global demand is the strongest, and how companies can build to best capture that demand. ## TBM 434: How Maps Can Hide Problems DevFeed: [TBM 434: How Maps Can Hide Problems]() Original publisher: [Read original article]() Author: John Cutler Published: 2026-08-01T09:13:07Z Content type: opinion Language: en Sources: [The Beautiful Mess]() Topics: [context](), [structure]() Tags: [design](), [mapping](), [maps](), [organizations](), [ownership](), [problems](), [product](), [reporting](), [silos](), [structure](), [technology]() ### AI overview The article argues that organizational maps can conceal incoherence when strategy, structure, technology, incentives, goals, ownership, teams, and funding do not align. It contrasts coherent organizations, where context transfers across map layers, with incoherent organizations, where people must repeatedly reorient and translate. ### Source excerpt If what you are mapping is incoherent, don't fall in love with the map (or your personal ability to navigate with it). ## Normalize security logs to Google SecOps UDM with Observability Pipelines DevFeed: [Normalize security logs to Google SecOps UDM with Observability Pipelines]() Original publisher: [Read original article]() Author: Danielle Park Published: 2026-07-27T00:00:00Z Content type: article Language: en Sources: [Datadog | The Monitor blog]() Topics: [telemetry]() Tags: [amazon-vpc](), [google-cloud](), [google-secops](), [logs](), [mapping](), [observability-pipelines](), [security](), [telemetry](), [threat-detection](), [vpc-flow-logs]() ### AI overview The article explains how Observability Pipelines Google SecOps packs normalize security logs into the Unified Data Model before they reach Google SecOps. ### Source excerpt Learn how Observability Pipelines normalizes your telemetry to Google SecOps UDM, enabling both consistent investigations across sources and precise upstream control over your SIEM ingest. ## Profunctor Optics DevFeed: [Profunctor Optics]() Original publisher: [Read original article]() Author: Bartosz Milewski Published: 2026-07-19T11:39:02Z Content type: article Language: en Sources: [Bartosz Milewski's Programming Cafe]() Topics: [Haskell](), [Programming language](), [Programming](), [modules]() Tags: [category-theory](), [haskell](), [language](), [lens](), [mapping](), [modules](), [optics](), [profunctors](), [programming-language](), [tambara-modules]() ### AI overview This article explains profunctor optics through Tannakian reconstruction. It presents optics as a category, describes lenses and their composition in Haskell, and introduces Tambara modules as a representation that simplifies optic composition. ### Source excerpt You may think of Tannakian Reconstruction as an example of redundant encoding. It lets you replace a simple hom-set with a much more complex end that is taken over an entire functor category. Why would anyone want to do it? The answer is simple: composition! Morphisms on the left compose according to the rules of [...] ## Expanding our Heat Resilience data to 50+ global cities DevFeed: [Expanding our Heat Resilience data to 50+ global cities]() Original publisher: [Read original article]() Published: 2026-06-30T17:03:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Earth AI](), [datasets](), [Artificial Intelligence](), [Google](), [App](), [data](), [Resilience]() Tags: [ai](), [app](), [climate-sustainability](), [data](), [datasets](), [earth-ai](), [google](), [heat](), [mapping](), [open](), [open-source-models-datasets](), [research](), [resilience](), [sustainability](), [tools]() ### AI overview Google Research is expanding its building-level rooftop reflectivity dataset to cover more than 50 global cities. The data is available through a high-resolution Heat Resilience Earth Engine App and is intended to help urban planners prioritize cool-roof interventions that reduce heat exposure and protect vulnerable communities. ### Source excerpt Climate & Sustainability ## Mapping Europe's AI Workforce Opportunity DevFeed: [Mapping Europe's AI Workforce Opportunity]() Original publisher: [Read original article]() Published: 2026-06-29T07:00:00Z Content type: article Language: en Sources: [OpenAI News]() Topics: [Artificial Intelligence](), [OpenAI](), [Automation](), [data]() Tags: [ai](), [automation](), [data](), [eu](), [europe](), [global-affairs](), [growth](), [mapping](), [openai](), [research]() ### AI overview OpenAI's AI Jobs Transition Framework for the EU uses the ESCO taxonomy and Eurostat employment data to map where AI may drive occupational growth, automation, workflow reorganization, or less immediate change across EU member states. ### Source excerpt A new OpenAI report maps how AI could reshape jobs across the EU, highlighting which occupations may face automation, growth, or workflow changes. ## Chat SDK adds Novu support DevFeed: [Chat SDK adds Novu support]() Original publisher: [Read original article]() Author: Ben Sabic Published: 2026-06-22T14:00:00Z Content type: release Language: en Sources: [Vercel News]() Topics: [SDKs](), [Command-line interface](), [Microsoft Teams](), [Slack]() Tags: [agent](), [bridge](), [channel](), [cli](), [documentation](), [identity](), [mapping](), [microsoft-teams](), [oauth](), [sdk](), [slack](), [support](), [telegram](), [tokens](), [whatsapp]() ### AI overview Chat SDK adds Novu support through a vendor-official adapter, allowing one handler set to connect agents to Slack, Microsoft Teams, WhatsApp, Telegram, and email. Novu manages credentials, identity, delivery, OAuth, and tokens, while a CLI command configures a channel and adds its credentials to the project. ### Source excerpt Chat SDK now supports Novu with the new vendor-official adapter. One handler set puts your agent on Slack, Microsoft Teams, WhatsApp, Telegram, and email. Novu handles credentials, identity, and delivery, keeping OAuth and tokens outside your app and mapping each channel to one user. Your agent always knows who they're talking to. Your agent can also send proactive notifications and handle the replies in the same loop, on whichever channel the customer used. One CLI command connects a real channel to your agent: It signs you in, creates a bridge agent, sets up the channel you pick (e.g., Slack), and adds the credentials to your project. Read the Novu documentation to get started. Read more ## Cloud Topics: the Metastore DevFeed: [Cloud Topics: the Metastore]() Original publisher: [Read original article]() Author: Andrew Wong Published: 2026-06-11T00:00:00Z Content type: article Language: en Sources: [Redpanda]() Topics: [Kafka](), [Cloud](), [rocksdb](), [data]() Tags: [architecture](), [cloud](), [consumer](), [engineering](), [kafka](), [learn](), [mapping](), [memory](), [object-storage](), [retention](), [rocksdb](), [scale](), [serialization](), [storage]() ### AI overview This article explains Redpanda's metastore for Cloud Topics. The metastore maps Apache Kafka offsets to byte ranges in L1 objects stored in object storage, while tracking metadata such as leader-term boundaries and compaction state. Redpanda built a general-purpose key-value store, inspired by LevelDB and RocksDB and implemented as an LSM tree, to scale metadata independently of memory, local disk, and metadata formats. ### Source excerpt Learn how Redpanda's metastore powers Cloud Topics, from offset lookups and whole cluster restore to cross-region read replicas, and why it's built to be a foundational primitive for the future. ## Mapping major CDNs across the globe DevFeed: [Mapping major CDNs across the globe]() Original publisher: [Read original article]() Published: 2026-06-06T13:17:04Z Content type: article Language: en Sources: [Personal blog of Anurag Bhatia]() Topics: [BGP](), [networking](), [Networks](), [Routing (disambiguation)](), [TLS (Transport Layer Security)](), [data](), [Amazon Web Services](), [Google](), [Netflix](), [Microsoft](), [Pingora]() Tags: [akamai](), [apple](), [aws](), [bgp](), [cdn](), [data](), [dns](), [facebook](), [fna](), [ggc](), [google](), [major](), [mapping](), [microsoft](), [netflix](), [networks](), [oca](), [routing](), [tls]() ### AI overview This article maps major content delivery networks worldwide by examining routed IP prefixes, open port 443 services, TLS certificate names, autonomous system numbers, and geographic data. It reports global and India-specific coverage figures for Google GGC, Facebook FNA/MNA, Netflix, Akamai, Apple, Microsoft, and AWS CloudFront, while noting that certificate-based identification may miss some deployments. ### Source excerpt In Dec 2022 I mapped popular CDNs like Google GGC, Facebook FNA, Akamai, etc. across Indian networks (post here). Since it's been close to 4 years now, I wanted to do that again. This time, I decided to expand the scope to the entire globe instead of just the Indian networks. Mapping logic The logic here is simple: get unique prefixes from the global routing table, break them into /24s, uniquely sort out /24s, and this gives all routed IP addresses in the world in batches of /24s (256 IPs). Next, identify the ones with an open port 443 and then connect to each of them to figure out the TLS certificate common name. Next, map those IP addresses to AS numbers, locations, etc., using Maxmind's GeoIP Lite databases. Essentially, I am using the BGP routing table instead of scanning the entire 0.0.0.0/0 to avoid scanning for prefixes which are not routed in the global table as well as reserved private IPs, etc. Global stats CDN Provider No. unique ASNs TLS domain Details list URL Google GGC 4247 googlevideo.com csv & json Netflix OCA 2903 oca.nflxvideo.net, assets.nflxext.com csv & json Facebook FNA 2548 'fbcdn.net', fna.whatsapp.net csv & json Akamai 1094 edgesuite.net, edgekey.net, akamaized.net, akamaihd.net, akamaized.net, akamai.net csv & json Microsoft 1655 microsoft.com csv & json Apple 974 apple.com & itunes.apple.com csv & json AWS Cloudfront 217 *.amazonaws.com & *.awsstatic.com csv & json ASN-CDN Mapping table I have mapped ASNs with the presence of each of these CDNs like last time. This makes it easy to read the data instead of going through each of the files separately. Full data in Google Sheet link here and raw CSV is also published here. Notes: Facebook FNA serving Facebook with *.fbcdn.net is almost the same if I look for *.fna.whatsapp.net. Apple seems to have presence in over 236 locations with PCH/Woodynet for hosting their DNS over HTTPS endpoint: doh.dns.apple.com (detailed list here) GGC has a global coverage across 215 countries across the world, f ## Tabulation Tribulations DevFeed: [Tabulation Tribulations]() Original publisher: [Read original article]() Author: Bartosz Milewski Published: 2026-05-23T16:05:49Z Content type: article Language: en Sources: [Bartosz Milewski's Programming Cafe]() Topics: [Graphs]() Tags: [category-theory](), [double-categories](), [graph](), [mapping](), [object](), [pairs](), [profunctor-equipment](), [profunctors]() ### AI overview This article explains tabulations in double categories by relating them to graphs of functions, relations, and profunctors. It describes the category of elements of a profunctor and introduces tabulation through projections and a universal property, including conditions for morphisms and 2-cells. ### Source excerpt Previously: Bending, Yanking, and Cartesian Squares in Double Categories. We all know what a graph of a function is: it's a set of pairs , where . Similarly, a graph of a relation is a set of pairs where is related to . A profunctor can be viewed as a proof-relevant relation. So a graph [...] ## How We Built a Smarter Pickup Experience for Gated Communities DevFeed: [How We Built a Smarter Pickup Experience for Gated Communities]() Original publisher: [Read original article]() Author: winnieyan Published: 2026-04-23T19:16:44Z Content type: article Language: en Sources: [Lyft Engineering - Medium]() Topics: [App](), [data](), [Routing (disambiguation)]() Tags: [app](), [data](), [how-to](), [lyft](), [mapping](), [metrics](), [rideshare](), [routing]() ### AI overview Lyft's Mapping team describes how it identified and addressed pickup problems at gated communities. The article highlights two root causes: inflexible pickup-spot recommendations and the lack of a way to share gate-access instructions before a ride. The proposed solution is an end-to-end app experience involving map data, pickup recommendations, routing, and rider and driver workflows. ### Source excerpt If you live in a gated community, you've been there: You request a ride from your apartment complex, expect your driver to come to you as usual, and then -- your driver's car icon just stops right at the front gate. You watch helplessly as the ETA ticks up. A chat message comes in: "Hey, how do I get in?" You scramble to remember the gate code. They try it. It doesn't work. You end up meeting them awkwardly on the sidewalk outside while your coffee gets cold -- a pickup journey frustrating for both you and your driver. An example gated community in real life, Photo by Bingqian Li on Pexels It turns out you're not alone: Gated community pickups can make up 25-30% of Lyft rides in selected markets. For a long time, our app offered no special guidance in these situations. Riders would drop their pin inside the gates (fair enough -- that's where they are), while drivers would pull up to a locked entrance with no way in, leaving both parties to sort things out over chat. The result was predictable: more cancellations, longer waits, and a lot of unnecessary stress for our customers. The Lyft Mapping team decided it was time to fix this properly -- not with a band-aid, but a new end-to-end experience. Here's how we did it. What Was Actually Going Wrong? We looked through gated ride examples, zoomed into our metrics data, and found two root causes behind most of the friction. The first was an inflexible selection of pickup spots. Our app would suggest pickup spots near a rider's location -- which, for riders inside a gated community, often means inside the gate. But our data told a different story: many riders actually preferred meeting their driver right outside the gate, knowing their driver couldn't access the property. The app wasn't giving them that option clearly. The second was a communication black hole. Even riders who knew how to get their driver through the gate had no good way to pass along access instructions in advance. Instead, they'd wait until the driver was alr ## AI-generated synthetic neurons speed up brain mapping DevFeed: [AI-generated synthetic neurons speed up brain mapping]() Original publisher: [Read original article]() Published: 2026-04-16T12:18:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Artificial Intelligence](), [AI Models](), [Google](), [Point cloud](), [Training AI Models](), [datasets](), [neuron](), [data]() Tags: [3d](), [accelerate](), [ai](), [classification](), [errors](), [general-science](), [generation](), [google](), [health-bioscience](), [iclr](), [iclr-2026](), [images](), [machine-intelligence](), [mapping](), [model](), [models](), [neuron](), [partners](), [research](), [scale](), [science](), [synthetic](), [visualization]() ### AI overview Google Research describes how MoGen generates synthetic neuronal shapes to improve AI models that reconstruct brain wiring maps. Adding synthetic training examples reduced reconstruction errors by 4.4%, potentially saving 157 person-years of manual proofreading for a complete mouse brain. ### Source excerpt General Science ## Mapping Brazilian Cell Towers DevFeed: [Mapping Brazilian Cell Towers]() Original publisher: [Read original article]() Author: Carlos Alexandro Becker Published: 2026-03-30T18:18:07Z Content type: opinion Language: en Sources: [Carlos Becker]() Topics: [data](), [Python](), [Cloudflare](), [Open Source](), [Front end]() Tags: [brazil](), [cities](), [cloudflare](), [data](), [data-pipeline](), [frontend](), [mapping](), [open-source](), [pages](), [python](), [tower]() ### AI overview The author describes building temsinal.org, an open-source map of Brazilian cell towers. It combines tower data from ANATEL with population and municipality data from IBGE to help people compare infrastructure, coverage claims, and local commitments. ### Source excerpt I was curious about how many cell towers were around me - so I built the tool I wanted. ## Mapping the modern world: How S2Vec learns the language of our cities DevFeed: [Mapping the modern world: How S2Vec learns the language of our cities]() Original publisher: [Read original article]() Published: 2026-03-24T17:42:00Z Content type: article Language: en Sources: [The latest research from Google]() Topics: [Embeddings](), [Earth AI](), [Google](), [multimodal](), [Machine Learning & Artificial Intelligence](), [foundation-models](), [data]() Tags: [ai](), [algorithms-theory](), [artificial-intelligence](), [data](), [earth-ai](), [embeddings](), [foundation-models](), [google](), [machine-intelligence](), [machine-learning](), [mapping](), [multimodal](), [research]() ### AI overview S2Vec is a self-supervised framework that converts complex geospatial data about the built environment into general-purpose embeddings. The article describes how these embeddings support prediction of socioeconomic and environmental patterns, while noting stronger results for geographic adaptation and remaining limitations on environmental tasks. ### Source excerpt Algorithms & Theory [Next page]()