Juanita Rondón

Carbon capture isn’t just waste disposal; it’s the ultimate circularity challenge. Most headlines focus on structural trapping shoving CO2 under a shale caprock and hoping the vault doesn't leak. True circularity means turning that gas back into a permanent geological feature through mineral trapping, where dissolved CO2 reacts with basalt or mafic rocks to form stable carbonate minerals. This creates a permanent geochemical lock stable for millennia. The bottleneck is that this process is naturally slow and depends heavily on specific reactive cations like Calcium, Magnesium, and Iron. To make this bankable, we need Intelligent Systems capable of dynamic geochemical simulations. We must predict exactly how pH shifts will trigger precipitation without clogging our injection pathways. Are we aiming for permanent mineral solutions, or are we just settling for temporary gas storage?

Hydrology has a dangerous sample size problem, and our Intelligent Systems are ignoring it. We are training AI to predict catastrophic 10,000-year events using datasets that are statistically anemic often spanning just 40 years. This isn't just a data gap; it’s a recipe for massive epistemic uncertainty. Most models still assume stationarity, but with urbanization spiking runoff potential and climate change shifting rainfall intensities, the baseline is a moving target. If we don't force AI to respect the physical limits of catchment-scale mass balance, we’re just building high-tech masks for low-probability disasters. No amount of data optimization can fix a model that hallucinates patterns in short-term noise. I think it is really important to train AI to respect the hard physics of water balance instead of just waiting the next extreme event to shatter our predictions

We thrive on Big Data, but hydrology has a dangerous sample size problem. We often use only 30 to 50 years of data to predict extreme 10,000-year flood events. Training AI models to extrapolate using statistical distributions into a non-stationary future driven by climate change creates massive epistemic uncertainty. Without quantifying parameter error through Monte Carlo simulations, we are building high-tech infrastructure on low-probability sand. We need to stop selling "certainty" in flood risk and start building Intelligent Systems that explicitly embrace the variance. Are we ready to admit our training sets are simply too short for the risks we face?

Are we ignoring catchment physics in AgriTech? We talk a lot about precision sensors and AI-driven yields, but long-term water balance is ultimately a zero-sum game between supply and atmospheric demand. Converting native forests to intensive pastures fundamentally shifts the Flow Duration Curve. We lose sustained baseflow and spike frequent high-flow events because the runoff potential increases. Too many "smart" irrigation systems try to optimize a catchment that is already out-of-phase with its seasonality. If Actual Evapotranspiration hits the physical water limit, no amount of digital optimization can innovate our way out of a hydrological deficit. Should we stop just optimizing the crop and start designing Intelligent Systems around the catchment’s natural regime? I’d love to hear from anyone integrating catchment-scale mass balance equations into farm management software.

The solution to urban heatwaves isn’t a futuristic magic bullet, it’s literally right over our heads! Geospatial modeling shows that Turin alone has over 15,450 buildings with the structural capacity for green roofs, yet only about 300 have implemented them. We are sitting on millions of square meters of dead "gray" space that could be actively slashing local temperatures. Extensive green roofs weigh less than 150 kg/m² and require minimal maintenance. They act as a passive climate intervention, dropping internal temperatures by up to 3°C to prevent heat stress. It’s the ultimate circularity play: repurposing wasted asset space for city resilience. Why is green roof adoption still treated as a luxury in urban planning rather than a mandatory infrastructure standard? Is the main barrier upfront cost, or are building codes simply stuck in the past?

We talk a lot about Intelligent Systems, but the real impact is in granularity. Now a days standard satellite data gives us a 30m resolution for urban heat! enough to see a neighborhood, but too coarse to see the actual risk on the street. Geospatial downscaling using Sentinel-2 and Landsat fusion is changing this. Heat doesn't care about averages; it cares about whether you’re standing on asphalt or under a green roof. In cities as Turin, in Italy, this tech proved that switching to high-albedo concrete blocks can slash surface temperatures by over 4°C. If we integrate these hyper-local thermal maps with public health and MedTech infrastructure, we could predict heat stress before it becomes an emergency room statistic. Are we actually embedding these datasets into active health and agri-tech apps, or are we just building pretty maps for urban planners?

Groundwater remediation is often treated as a bureaucratic checklist rather than what it truly is: preventative MedTech. When dealing with contaminated sites, companies usually focus on hitting regulatory limits e.g. Italy’s D.Lgs. 152/06. However, the bottleneck lies in the residual phase as NAPL, trapped pockets of pollutants feeding toxic plumes for decades. Relying on Monitored Natural Attenuation is essentially giving palliative care to an aquifer instead of a permanent cure. Healthcare demand absolute precision and active treatment. It would be interesting to apply that same rigor to subsurface engineering, using aggressive source removal like In Situ Chemical Oxidation to target the actual biological risk to human health. Sometimes it seems we are too comfortable settling for minimum regulatory thresholds when we may have the tech to deliver a full recovery.

We need to stop thinking of Carbon Capture as just waste disposal. It’s indeed an Intelligent Systems problem. The ultimate circularity challenge is managing the CO2 we’ve already emitted. As is the case of deep saline aquifers, which are our best "vaults" for storage, the real hurdle isn’t the injection, it’s predicting how that gas moves over millennia. We are dealing with dynamic geochemical variables that require real-time 3D monitoring to ensure the containment doesn't leak. Without high-fidelity data to track plume migration, the carbon-neutral promise lacks safety at a geological timescale. Are we investing enough in the AI-driven monitoring tech needed to make storage truly bankable? I'd love to hear from anyone working on subsurface sensor-fusion.