Using technology to offset weather data shortages

In 2022, I was part of a research team that took on a critical challenge: 𝐡𝐨𝐰 𝐝𝐨 𝐲𝐨𝐮 𝐚𝐬𝐬𝐞𝐬𝐬 𝐫𝐚𝐢𝐧𝐟𝐚𝐥𝐥 𝐢𝐧 𝐫𝐞𝐠𝐢𝐨𝐧𝐬 𝐰𝐡𝐞𝐫𝐞 𝐫𝐚𝐢𝐧 𝐠𝐚𝐮𝐠𝐞𝐬 𝐚𝐫𝐞 𝐬𝐜𝐚𝐫𝐜𝐞? Our focus was Sudan, a country where climate-driven decisions are crucial, but data gaps make it difficult to plan and prepare. We turned to satellite and gridded rainfall datasets, tools that have become essential in modern hydroclimatic research. What we found was both promising and eye-opening. 📍 While most rainfall products showed a tendency to underestimate rainfall, especially on annual and monthly scales, two stood out: 𝐂𝐇𝐈𝐑𝐏𝐒 𝐚𝐧𝐝 𝐂𝐑𝐔 𝐝𝐚𝐭𝐚𝐬𝐞𝐭𝐬 consistently performed best, especially in the western and southern regions of Sudan. 🌧️ We discovered that summer rainfall (the main rainy season) is captured more accurately than annual totals, especially in mountainous areas. And when we explored deeper, we noticed a significant link between rainfall trends and the Atlantic Multidecadal Oscillation (AMO), with some regions showing correlations as high as 90%. This was more than just data and numbers; it was a reflection of how remote sensing, when used wisely, can support 𝐜𝐥𝐢𝐦𝐚𝐭𝐞 𝐫𝐞𝐬𝐢𝐥𝐢𝐞𝐧𝐜𝐞, 𝐟𝐨𝐨𝐝 𝐬𝐞𝐜𝐮𝐫𝐢𝐭𝐲, 𝐚𝐧𝐝 𝐫𝐢𝐬𝐤 𝐩𝐫𝐞𝐩𝐚𝐫𝐞𝐝𝐧𝐞𝐬𝐬 in the very places that need it most. 🔍 The study underscored the value of CHIRPS data for monitoring rainfall variability and extreme events, and why it should be a go-to resource for decision-makers in data-scarce environments. Being part of this work reminded me of the power of science and collaboration in driving evidence-based action. It’s research like this that fuels real-world solutions, and I’m proud to have contributed to it.  Richard Anyah Mohamed Abdallah Ahmed Alriah, PhD Aslak Grinsted Hans Hersbach Lorenz Ewers Victor Ongoma Nixon Mutai #ClimateResearch #RainfallData #RemoteSensing #Sudan #ClimateResilience #CHIRPS #Hydroclimatology #SatelliteData #ClimateScience #DataForDevelopment

Digital skills aren’t just powering businesses. They are strengthening climate resilience. In the face of rising temperatures and extreme weather, small holder farmers need better tools to adapt and plan. But many regions still lack the local data needed to inform decisions about planting, harvesting, and protecting crops. That is why I am inspired by the work of Cisco Foundation grantee One Acre Fund, which is using remote sensing technology to support precision agriculture. Their approach includes flood mapping, digital weather advisories, and crop yield monitoring, helping farmers respond to climate risks with better information. In Kenya, more than 10,000 farmers now receive weather updates. Thousands of flood data points have been mapped. And pilots are already underway in four additional countries. When we pair digital tools with community-driven solutions, we unlock powerful potential for impact. #DigitalSkills #ClimateResilience #TechForGood

Most weather forecasts rely on complex data assimilation (DA) to fill in the gaps between sparse observations. But DA is inherently limited, relying on incomplete inputs, delayed updates, and assumptions. It's like watching a movie with only a handful of frames and guessing what happens in between. We're taking a fundamentally different approach: We don't guess. We observe. The attached visualization captures one day of observations from three of our operational satellites (we now have six!), scanning the globe every five minutes at 2.5km resolution. While traditional systems wait for DA cycles to process incomplete data, our satellites enable real-time inference—where AI models generate forecasts from actual observations, not estimates. By the end of 2025, our global constellation will achieve sub hourly revisit rate, eliminating remaining blind spots, and will deliver truly global, real-time weather intelligence. The tech industry is learning what we already know: in the age of commoditized AI, proprietary data is the ultimate moat.

🌍 Simulating River Basins Without Outlet Data: Challenges and Cutting-Edge Solutions 🌊 The absence of outlet data for river basins poses a significant challenge in hydrologic and hydraulic modeling. Without this critical dataset, traditional methods of model calibration and validation become less viable. However, advancements in technology and innovative methodologies are offering promising alternatives. Here are some key approaches experts are adopting to address this challenge: ✅ Distributed Hydrologic Modelling: Breaking down basins into smaller units for localised flow estimation, reducing reliance on outlet data. ✅ Remote Sensing Integration: Leveraging satellite-derived data such as precipitation, soil moisture, and vegetation indices as proxies for flow conditions. ✅ Regional Parameterisation: Applying insights from similar, well-monitored basins to estimate parameters for under-monitored areas. ✅ Data Assimilation Techniques: Combining reanalysis datasets with limited field observations to improve model accuracy. ✅ Machine Learning Applications: Employing data-driven models to predict flows based on climatic and topographic variables. These methods not only enable robust modelling in data-scarce regions but also highlight the critical role of geospatial technologies and innovative research in water resource management. As the global climate continues to change, improving our ability to model and predict hydrological behaviour in unmonitored basins is essential for flood risk management, water allocation, and sustainability planning. What emerging techniques or tools have you found effective in addressing data gaps in hydrology? Let’s exchange insights and advance our field together! #Hydrology #DataScarcity #WaterResources #FloodRisk #RemoteSensing #GeospatialTechnology

We're seeing a fundamental shift in weather forecasting, moving from broad regional predictions to incredibly precise, hyperlocal data. As a recent The Wall Street Journal article highlighted, we're now talking about predicting conditions for a city block, or even your own backyard. This isn't just an academic exercise. Industries from drone delivery, where 25% of downtime is weather-related, to agriculture and critical infrastructure, are demanding this level of granularity. They need to understand wind at 50 meters, or rainfall specific to one field, to operate safely and efficiently. What's driving this? A powerful confluence of new data sources like IoT sensors, local mesonets, and LIDAR, combined with breakthroughs in AI and machine learning. Even crowdsourced data from smartphones is playing a role. This is creating a vast, real-time picture of atmospheric conditions that was simply impossible a few years ago. This is where initiatives like WeatherXM become especially important. By building a decentralized network of weather stations globally, they are not only producing vital hyperlocal data that can feed use cases like drone navigation, but also creating a model where the community supporting this expansion can generate revenue. This kind of collaborative, incentive-aligned data infrastructure is a powerful enabler for the future. For those of us building and supporting ventures, particularly in deep tech and climate tech, the timing on this is critical. Access to this hyperlocal weather intelligence is no longer a luxury; it's becoming a necessity for optimizing operations, mitigating risk, and unlocking new business models. It’s about leveraging data to build more resilient and efficient systems in a world that demands precision. This is a space ripe for founders. PM if you are building in this space!

☁️ Clouds block satellites. Floods don’t care. Here’s how foundation models are being adapted to see through the storm. During extreme weather events like floods, clouds often block optical satellites from capturing usable data. And that's exactly when timely insight matters most. Originally shared by Heather Couture, PhD, this study tackled this head-on. It adapted the Prithvi foundation model, originally trained on optical imagery, by incorporating Synthetic Aperture Radar (SAR) to detect floods across the UK and Ireland. ✅ SAR can “see” through clouds ✅ Fine-tuning the model with SAR bands boosted flood segmentation accuracy from 0.58 to 0.79 ✅ Even small amounts of local data were enough to adapt the model to new regions This research shows that Earth Observation Foundation Models can be effectively adapted for disaster response, even in data scarce areas and how AI can be useful for real world problems. 🌎 I'm Matt and I talk about modern GIS, AI, and how geospatial is changing. 📬 Want more like this? Join 6k+ others learning from my newsletter → forrest.nyc

It doesn't take much reflection to realise that accurately predicting the weather is an awesomely complex problem. The state of the art systems today still rely heavily on numerical solvers which make the pipelines complex, slow and very computationally expensive to run. This means that while well-resourced countries can afford to produce high-resolution regional models there are significant limitations in places like West African and parts of the Pacific. So it's really exciting to read about Aardvark Weather, the first end-to-end data driven weather prediction system that offers complete replacement of the numerical weather prediction pipeline. "The simplicity of this system both makes it both easier to deploy and maintain for users already running NWP, and also opens the potential for wider access to running bespoke NWP in areas of the developing world where agencies often lack the resources and expertise to run conventional systems. There is also significant potential in the demonstrated ability to fine-tune bespoke models to maximise predictive skill for specific regions and variables. This capability is of interest to many end users in areas as diverse as agriculture, renewable energy, insurance and finance." Happily Nature has provided open access to the preprint so you can read more detail there. https://lnkd.in/gJXSS8BS

Accurate weather forecasts are not just about predicting rain or sunshine—they are about saving lives, protecting livelihoods, and building resilience in the face of climate change. Yet, many regions of the world remain "blind spots" in the global weather observation system, leaving communities vulnerable and forecasts less effective. The latest impact experiments conducted by the European Centre for Medium-Range Weather Forecasts (ECMWF), commissioned by the World Meteorological Organization (WMO), provide the strongest scientific evidence yet: investing in weather and climate observations in under-resourced regions significantly improves forecast accuracy—both locally and globally. Through the Systematic Observations Financing Facility (SOFF), we are addressing these gaps by supporting Least Developed Countries (LDCs) and Small Island Developing States (SIDS) to generate and share critical weather data. The ECMWF experiments confirm that these investments are not just local solutions—they are global game-changers. For example: Forecast uncertainty decreases by over 30% in Africa and up to 20% in the Pacific Islands with improved observations. Upper-air data, such as radiosonde observations, has an outsized impact, especially in tropical regions. Local investments lead to global benefits, improving forecast accuracy worldwide. These findings reaffirm the WMO’s commitment to ensuring that no country is left behind in the global effort to strengthen early warning systems and climate resilience. By expanding SOFF investments, we can close the data gap, enhance global forecasting capabilities, and protect communities from the increasing risks of extreme weather events. As we move forward, I invite governments, development partners, and the private sector to join us in this mission. Together, we can ensure that every region, no matter how remote, contributes to and benefits from a stronger, more connected global weather observation system: https://lnkd.in/d_FSHkE2

Since launch, Tomorrow.io has been steadily expanding the reach and revisit rate of our microwave sounder constellation. That progress is already delivering value - driving improvement in both global and regional models and allowing national meteorological services improved visibility where it’s needed most. Here are two recent examples from our team: - A scan over Europe taken on May 20th, capturing the evolution of frontal boundaries and moisture gradients from mid-latitude systems across the Mediterranean and North Atlantic - A scan over the Caribbean and Central America taken on May 20th, showing tropical convection over the Caribbean and Pacific systems approaching Central America, both linked to heavy rainfall These visualizations offer a glimpse into the kind of impact our technology is designed to deliver. With cloud-penetrating, high-frequency observations from mixed-inclination orbits, our constellation fills gaps left by geostationary and conventional polar-orbiting satellites - bringing visibility to fast-evolving weather across data-sparse regions. This isn’t just a data feed - it’s an evolving global system built to enable faster decisions, better preparedness, and stronger resilience in the face of extreme weather. Much more to come. 🌍