Alternatives
Products that do what Atlas of Water Science via generative AI does
This is our Atlas of Water Science. It's a globe mapping water science that colleagues have done over the past few years. Approx 300 papers got analyzed. The pipeline sends open access papers to an LLM asks the LLM to extract areas relevant to science in a form suitable for a geocoder, then we use a geocoder to get lat lons. When things happen in the same spot we jitter the locations a bit to differentiate things. gpt4o-mini was used for most of the analysis. Some of the features on the website are directly invented by Claude. There are some errors when geocoding went wrong or locations were…
- 1
- 2
- 3
- 4IM
Hey HN! I love finding new books to read on here. I wanted to gather the most mentioned books and recreate the serendipity of physical browsing. I scraped 20k comments from HN threads related to reading, extracted the references and opinions using GPT-4o mini, and visualised their embeddings as a map. - OpenAI's embeddings were processed using UMAP and HDBSCAN. A direct 2D projection from the text embeddings didn't yield visually interesting results. Instead, HDBSCAN is first applied on a high-dimensional projection. Those clusters tend to correspond to different genres. The genre…
2024 · hnbooks.pieterma.es
- 5KG
Hi HN! My latest side project is knowledge graph that maps the French culinary network using data extracted from restaurant reviews from LeFooding.com. The project uses LLMs to extract structured information from unstructured text. Some technical aspects you may be interested in: - Used structured generation to reliably parse unstructured text into a consistent schema - Tested multiple models (Mistral-7B-v0.3, Llama3.2-3B, gpt4o-mini) for information extraction - Created an interactive visualization using gephi-lite and Retina (WebGL) - Built (with Claude) a simple Flask web app to clean and…
2025 · theophilecantelob.re
- 6SI
I built a browser-based tool for detecting objects in satellite imagery using vision-language models (VLMs). You draw a polygon on the map and enter a text prompt such as "swimming pools", "oil tanks", or "buses". The system scans the selected area tile-by-tile and returns detections projected back onto the map as GeoJSON. Pipeline: select area and zoom level, split the region into mercantile tiles, run each tile with the prompt through a VLM, convert predicted bounding boxes to geographic coordinates (WGS84), and render the results back on the map. It works reasonably well for distinct…
Mar 2026 · useful-ai-tools.com
- 7
- 8MD
2023 · louisquissetlabs.com
- 9
- 10
- 11G3
I made a web app to generate 3D models of real places on earth from land cover and elevation data. Click anywhere on the map to get a polygon, and then click "generate". It should work at most scales, but if your watershed or region selection is too large, the result can be less exciting because it's so flat. As a warning, the 3D models can sometimes be too much for my phone. It's nicer on desktop. I'm still working better on mobile support. The land cover data I'm using gives a cool effect, but at some point I'd like to add in global imagery and clouds. The backend is a Python thread…
2025 · topography.jessekv.com
- 12IG
2024 · columns.ai
- 13
- 14
- 15IJ
Hi HackerNews, Lately, I have seen an explosion in posts offering paid APIs/services to get unstructured data into LLMs (i.e. langchain extract, ragflow, unstructured, unstract, just to name a few) and I have been largely disappointed by them, either because they fail to implement multimodal support, fail to give good context for "really tricky" PDFs / Word docs / Powerpoints, or are just plain difficult to use. In light of all these posts I figured I'd share my solution that has been working smoothly for me and my clients. I put it up on GitHub for free so you can check it…
2024 · github.com
- 16UD
We can now build drastically higher quality search because we can use LLMs in algorithms that mimic a human's systematic research process, instead of just roughly recommending results based on semantic embeddings or term frequency. We built a deep search LLM pipeline that takes a few minutes to carefully search all the scientific literature. You describe your complex goal, as you would to a colleague. Then, we carefully search 200M+ papers. We classify the preliminary results with GPT-4. We then adapt the search goals based on relevant/irrelevant papers uncovered and continue searching,…
2024 · undermind.ai
- 17
- 18MO
We built Maptoolkit.org - a free, production-grade vector maps service built on OpenStreetMap and MapLibre. Map rendering and tile hosting have historically been either expensive (Google, Mapbox) or complex to maintain yourself. (Plus: Their maps are car-focused.) Our maps feature max data zoom 15, global hill-shading, 3D terrain, contour lines, water depths, and specialized styles (like Hiking, Cycling, Winter). No sign up or API keys required. You can use it like this: ``` const map = new maplibregl.Map({ container: 'map', style: 'https://styles.maptoolkit.org/summer.json',…
Jul 2026 · maptoolkit.org
- 19AO
I've recently been working with real-time geoJSON data at a rate of 50+ queries per second. SaaS solutions can be prohibitively expensive at this rate, thus, I created go-reverse-geo. Data is pulled from geonames.org and is stored in MongoDB (a requirement of my current project). It is very much a work-in-progress (I wrote it this morning). Hope someone finds it useful. https://paranoia.dev/vivi/go-reverse-geo
2020
- 20
A free topographic map of the latest 10M+ research papers
May 2026 · globalresearchspace.com
- 21FG
Oct 2025 · amplitude.com
- 22FD
I'm not a geospatial expert — I work in AI/ML. This started when I was exploring LiDAR data with agentic assitince and noticed that different signal decomposition methods revealed different terrain features. The core idea: if you systematically combine decomposition methods (Gaussian, bilateral, wavelet, morphological, etc.) with different upsampling techniques, each combination has characteristic "failure modes" that selectively preserve or eliminate certain features. The differences between outputs become feature-specific filters. The framework tests 25 decomposition × 19 upsampling…
Jan 2026 · github.com
- 23GJ
2018 · github.com
- 24MO
Hi HN! We're happy to announce the launch of Mapedia.org, an open source crowdsourced learning map! Mapedia is a new kind of learning platform at the crossroad between Wikipedia, Google Maps and Khan Academy: a learning map built collaboratively to support online learners to learn any topic seamlessly. We built an interactive learning map of topics to be able to visualize the different fields of knowledge, what concepts are included in them and how they relate to each other. This allows for curiosity based exploration, identifying knowledge gaps (unknown unknowns) and figuring out what to…
2022 · mapedia.org
Ranked by how close each launch is in meaning, then by votes. Refine with a description →