Launch HN: Constellation Space (YC W26) – AI for satellite mission assurance | Hacker NewsHacker Newsnew | past | comments | ask | show | jobs | submitloginLaunch HN: Constellation Space (YC W26) – AI for satellite mission assurance40 points by kmajid 17 hours ago | hide | past | favorite | 15 commentsHi HN! We're Kamran, Raaid, Laith, and Omeed from Constellation Space (https://constellation-io.com/). We built an AI system that predicts satellite link failures before they happen. Here's a video walkthrough: https://www.youtube.com/watch?v=069V9fADAtM.Between us, we've spent years working on satellite operations at SpaceX, Blue Origin, and NASA. At SpaceX, we managed constellation health for Starlink. At Blue, we worked on next-gen test infra for New Glenn. At NASA, we dealt with deep space communications. The same problem kept coming up: by the time you notice a link is degrading, you've often already lost data.The core issue is that satellite RF links are affected by dozens of interacting variables. A satellite passes overhead, and you need to predict whether the link will hold for the next few minutes. That depends on: the orbital geometry (elevation angle changes constantly), tropospheric attenuation (humidity affects signal loss via ITU-R P.676), rain fade (calculated via ITU-R P.618 - rain rates in mm/hr translate directly to dB of loss at Ka-band and above), ionospheric scintillation (we track the KP index from magnetometer networks), and network congestion on top of all that.The traditional approach is reactive. Operators watch dashboards, and when SNR drops below a threshold, they manually reroute traffic or switch to a backup link. With 10,000 satellites in orbit today and 70,000+ projected by 2030, this doesn't scale.
Our system ingests telemetry at around 100,000 messages per second from satellites, ground stations, weather radar, IoT humidity sensors, and space weather monitors. We run physics-based models in real-time - the full link budget equations, ITU atmospheric standards, orbital propagation - to compute what should be happening. Then we layer ML models on top, trained on billions of data points from actual multi-orbit operations.The ML piece is where it gets interesting. We use federated learning because constellation operators (understandably) don't want to share raw telemetry. Each constellation trains local models on their own data, and we aggregate only the high-level patterns. This gives us transfer learning across different orbit types and frequency bands - learnings from LEO Ka-band links help optimize MEO or GEO operations.
We can predict most link failures 3-5 minutes out with >90% accuracy, which gives enough time to reroute traffic before data loss. The system is fully containerized (Docker/Kubernetes) and deploys on-premise for air-gapped environments, on GovCloud (AWS GovCloud, Azure Government), or standard commercial clouds.Right now we're testing with defense and commercial partners. The dashboard shows real-time link health, forecasts at 60/180/300 seconds out, and root cause analysis (is this rain fade? satellite setting below horizon? congestion?). We expose everything via API - telemetry ingestion, predictions, topology snapshots, even an LLM chat endpoint for natural language troubleshooting.The hard parts we're still working on: prediction accuracy degrades for longer time horizons (beyond 5 minutes gets dicey), we need more labeled failure data for rare edge cases, and the federated learning setup requires careful orchestration across different operators' security boundaries.
We'd love feedback from anyone who's worked on satellite ops, RF link modeling, or time-series prediction at scale. What are we missing? What would make this actually useful in a production NOC environment?Happy to answer any technical questions!

1yvino 15 hours ago | next [–]
pretty intriguing demo video. how do you ensure your telemetry ingestion happens operationally that will be daunting task. output will be as good as your telemetry any delay or break in data everything bound break.replykmajid 14 hours ago | parent | next [–]
Great point, telemetry reliability is the biggest hurdle for any mission-critical system. We address the "garbage in, garbage out" risk by prioritizing freshness (our pipeline treats latency as a failure).We use a"leaky" buffer strategy (if data is too old to be actionable for a 3-minute forecast, we drop it to ensure the models aren't lagging behind the physical reality of the link),graceful degradation (when telemetry is delayed or broken, the system automatically falls back to physics-only models i.e. orbital propagation and ITU standards), andedge validation (we validate and normalize data at the ingestion point, if a stream becomes corrupted or "noisy," the system flags that specific sensor as unreliable and adjusts the prediction confidence scores in real-time).replyverzali 12 hours ago | prev | next [–]
Rather than longer times, what about short times? I did some work on fast fading and you can see rapid swings in fade over <5s. That is hard for automated systems to respond to, so you normally respond by increasing the link margin. If you can predict this you could reduce the margin needed. That could potentially be very valuable.replykmajid 12 hours ago | parent | next [–]
Spot on. We categorize that <5s window as tactical fade mitigation.Our current 3-5m window is for topology/routing, but the sub-5s window is for Dynamic Link Margin (DLM). If we can predict fast-fading signatures—like tropospheric scintillation or edge-of-cloud diffraction, we can move from reactive to proactive ACM.replydsrtslnd23 11 hours ago | prev | next [–]
Is the inference running on-orbit or ground-side? I guess SWaP is a major constraint for the former. Not sure if you are using FPGAs or something like a Jetson?replykmajid 8 hours ago | parent | next [–]
Primary inference runs ground-side (K8s/GovCloud) to aggregate global data for routing. We do see the need for something like a hybrid-edge approach for tactical, sub-5s mitigation. We would target FPGAs (like Xilinx Versal) for production flight hardware to meet strict SWaP and radiation-hardening requirements.replyfree_energy_min 14 hours ago | prev | next [–]
Very cool company! Are y’all hiring?replykmajid 12 hours ago | parent | next [–]
Not right now but we will be soon! Send over your resume to hello@constellation-io.com if you're interested in joining.replyJumpCrisscross 13 hours ago | prev | next [–]
Are you raising?replykmajid 12 hours ago | parent | next [–]
Not currently, we're planning on opening up our seed round in 4 weeks, feel free to shoot us a note at hello@constellation-io.com if you're interested in learning more.replyJumpCrisscross 7 hours ago | root | parent | next [–]
Done (XX:56).replyinfinitewars 13 hours ago | prev [–]
Do you plan to work on orbital weapon systems like Golden Dome?replykmajid 12 hours ago | parent [–]
We're big believers in American Dynamism.replydylan604 10 hours ago | root | parent [–]
you could have used a one word answer, yes. the extra words could have been "if we can get it".in other words, you're not opposed to working in the military industrial complex. your reply walks the line of weasel words. trying not to offend those against while nodding to those that approve. you'll do fine as a spokepersonreplykmajid 9 hours ago | root | parent [–]
You get it!reply

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact
Search:

Constellation Space, founded by Kamran, Raaid, Laith, and Omeed and currently operating within the YC W26 cohort, is developing an AI-powered system designed to predict satellite link failures before they occur. The company targets the escalating challenges presented by the rapidly expanding number of satellites in orbit – projected to reach 70,000 by 2030 – by providing proactive solutions for mission assurance. The core issue they address is the reactive nature of traditional satellite operations, where operators typically only respond to link degradation after it has already manifested, often resulting in lost data.

The system’s foundation rests on the complex interplay of variables affecting satellite RF links, including orbital geometry, tropospheric attenuation, rain fade, and ionospheric scintillation. The team leverages years of experience from its founders’ previous roles at SpaceX, Blue Origin, and NASA to capture these factors. They ingest approximately 100,000 telemetry messages per second from satellites, ground stations, weather radar, IoT humidity sensors, and space weather monitors, processing this data to forecast link health.

A key element of Constellation Space's approach is its utilization of federated learning. Recognizing the sensitivity of telemetry data, operators contribute to model training without sharing raw data. Each constellation trains local models, and only high-level patterns are aggregated, enabling transfer learning across different orbit types and frequency bands. This approach allows learnings from LEO Ka-band links to optimize MEO or GEO operations.

The system's primary inference runs on-premise within a Kubernetes environment on GovCloud, prioritizing data security and aggregation for global routing. However, the team acknowledges the need for a hybrid-edge approach, specifically targeting FPGAs (such as Xilinx Versal) for flight-critical hardware to meet stringent SWaP (Size, Weight, and Power) requirements and radiation-hardening stipulations. They are currently focusing on predicting link failures 3-5 minutes out with >90% accuracy, providing sufficient time for rerouting traffic and preventing data loss.

The system’s dashboard presents real-time link health, forecasts extending to 60, 180, and 300 seconds out, and root cause analysis, differentiating between issues like rain fade, satellite position below the horizon, or network congestion. Moreover, it exposes this information via an API, facilitating telemetry ingestion, predictions, topology snapshots, and even a natural language chat endpoint for troubleshooting. The team is actively working to improve prediction accuracy beyond the 5-minute timeframe and to acquire more labeled failure data for rare edge cases. They are particularly interested in incorporating tactical fade mitigation, addressing fast fading signatures that occur within the <5s timeframe.

Constellation Space is currently participating in testing with defense and commercial partners, and they’re planning a seed round launch in four weeks, inviting interested investors to contact them at hello@constellation-io.com.