Drop 40 NetCDF ensemble members on the canvas, crop them to your region, aggregate to seasonal means, and difference each against a 1991–2020 baseline — every step a live node. Deliver a small-multiple map grid and a per-region anomaly CSV the report pulls straight in. Rerun the lot on next year's ensemble by dropping the new files.
Climate signals live in the spread, not in any single run. One member can show a wet season where the ensemble mean shows dry; the honest answer is the whole distribution of 40. But the moment you have 40 files, the analysis usually fractures into a pile of notebooks only their author can rerun — and the reviewer never sees why one panel looks off.
In LSD the 40 members are one entity with a member axis, so the region crop, the seasonal aggregation, and the baseline difference each apply across all of them at once. Every node caches its intermediate, so nudging the season definition or the color limits repaints the small-multiples without re-reading a byte from disk. You end up looking at the ensemble instead of waiting on it.
Any CF-compliant NetCDF ensemble works — CMIP6 members, a regional downscaling run, or your own perturbed-physics set. You'll want a baseline climatology on the same grid; a 1991–2020 mean is the usual pick. The sample project ships a 40-member near-surface-temperature set at monthly cadence, and the full pipeline reruns end to end in a few seconds.
Drag the folder of 40 NetCDF members onto the canvas. The @load node stacks them into one entity along a member axis, reads headers only, and previews near-surface temperature with its lat, lon, and time dimensions. Forty files become one thing you can slice.
Add a @shape crop node and drag a lat/lon box over the region in the map preview, snapping it to the basin you care about. All 40 members crop together and the preview redraws as you drag. The global grid stays on disk as a cached intermediate, so nothing gets copied.
Chain a group-and-aggregate node keyed on season — DJF, MAM, JJA, SON — with the reducer set to mean. The monthly time axis collapses to four seasonal fields per member. Switch the reducer to a high percentile instead and the whole matrix recomputes live.
Drop the 1991–2020 climatology as a second @load and wire a @shape expression that subtracts it — anomaly = season_mean - baseline. Expose the baseline period as a live parameter. Every member's map recolors around zero the moment you connect the node.
Add a @deliver map node and set it to facet by member. Forty little anomaly maps tile into one figure with a shared diverging colorbar, so the spread across the ensemble reads at a glance. Nudge the color limits once and every panel follows.
Drop region polygons on a zonal-stats node and it rolls each member's anomaly up to a per-region mean. Wire that into a @deliver CSV — one row per region and member — that the report pulls straight in. Next year's ensemble drops onto the same canvas and both outputs rebuild.
Stack 40 ensemble members into one entity, reading headers first and arrays only when a step needs them.
Crop every member to the region, collapse months into seasonal means, and difference each against the baseline climatology.
Tile a small-multiple anomaly map grid and export a per-region anomaly table for the report.
Slice 200 GB of NetCDF CFD output into live wake planes and iso-surfaces, then export an animated wake visualization and a downstream-loss table.
Model post-closure pit-lake rebound in LSD — krige borehole heads against a NetCDF recharge grid and deliver a live 3D drawdown model plus report.
Validate 63 LAS drillhole logs against collar surveys, krige a lithology block model, and export one glTF the whole team can open.
Build churn features from Postgres events and Parquet snapshots, catch a leaky window visually, and score the holdout with ONNX — on one canvas.
Score a million-row Parquet batch with an ONNX model — training-identical normalization, live previews, scored Parquet and metrics out.
Turn raw LAS/LAZ sweeps from a mobile robot into a nav-ready occupancy grid and 3D map — registration to export with zero scripts.
Sync CSV sensor logs with live REST telemetry, flag outliers and dropouts, and score every robot pass/fail before the field trial.
Turn folders of line-scan images and a label CSV into an ONNX defect-segmentation pipeline with overlay QA and a per-coil defect report.
Turn GeoTIFF orthomosaics into a stitched land-cover raster with per-class area stats, using tiled ONNX segmentation you can preview at every step.
Align CMM measurement points to a nominal CAD mesh, compute point-to-surface deviation, and export a color-mapped glTF model with a pass/fail report.
Resample a week of machine sensor logs, baseline each tag, and flag drift and step changes on a live dashboard with a ranked maintenance shortlist.
Join a live meter feed to 85 campus building meshes, aggregate it hourly, and paint a 3D heat-map that repaints as energy use shifts, plus a weekly report.
Drag the folder of 40 NetCDF members onto the canvas. The @load node stacks them into one entity along a member axis, reads headers only, and previews near-surface temperature with its lat, lon, and time dimensions. Forty files become one thing you can slice.
Add a @shape crop node and drag a lat/lon box over the region in the map preview, snapping it to the basin you care about. All 40 members crop together and the preview redraws as you drag. The global grid stays on disk as a cached intermediate, so nothing gets copied.
Drop the 1991–2020 climatology as a second @load and wire a @shape expression that subtracts it — anomaly = season_mean - baseline. Expose the baseline period as a live parameter. Every member's map recolors around zero the moment you connect the node.
Add a @deliver map node and set it to facet by member. Forty little anomaly maps tile into one figure with a shared diverging colorbar, so the spread across the ensemble reads at a glance. Nudge the color limits once and every panel follows.