44:I[603186,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/268l5ccisytc0.js","/_next/static/chunks/2b4d1e9ztz65u.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/2g-r6rokjl78a.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/03uy_tk5mi4gg.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0irw7vnh9fzo0.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1i60vi-4s7c4l.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],"PageMetadata"] 45:I[831915,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/268l5ccisytc0.js","/_next/static/chunks/2b4d1e9ztz65u.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/2g-r6rokjl78a.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/03uy_tk5mi4gg.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0irw7vnh9fzo0.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1i60vi-4s7c4l.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],"SearchResultsImage"] 46:I[430295,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/268l5ccisytc0.js","/_next/static/chunks/2b4d1e9ztz65u.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/2g-r6rokjl78a.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/03uy_tk5mi4gg.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0irw7vnh9fzo0.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1i60vi-4s7c4l.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],""] 47:I[299632,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/268l5ccisytc0.js","/_next/static/chunks/2b4d1e9ztz65u.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/2g-r6rokjl78a.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/03uy_tk5mi4gg.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0irw7vnh9fzo0.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1i60vi-4s7c4l.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],"default"] 48:I[400402,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/268l5ccisytc0.js","/_next/static/chunks/2b4d1e9ztz65u.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/2g-r6rokjl78a.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/03uy_tk5mi4gg.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0irw7vnh9fzo0.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1i60vi-4s7c4l.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],"EndpointCTA"] 49:I[331699,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/268l5ccisytc0.js","/_next/static/chunks/2b4d1e9ztz65u.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/2g-r6rokjl78a.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/03uy_tk5mi4gg.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0irw7vnh9fzo0.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1i60vi-4s7c4l.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],"ModelContent"] 51:I[946424,["/_next/static/chunks/27gl9k2703ugd.js","/_next/static/chunks/3pd35vh8xvq70.js","/_next/static/chunks/268l5ccisytc0.js","/_next/static/chunks/2b4d1e9ztz65u.js","/_next/static/chunks/24mqrfe34h1_g.js","/_next/static/chunks/1la1pzs9j8idc.js","/_next/static/chunks/3-axx3uk1c0-h.js","/_next/static/chunks/14bn3mp7hfp6x.js","/_next/static/chunks/1_xj2c5utin8v.js","/_next/static/chunks/2tdv_pqf9hlyu.js","/_next/static/chunks/44n8gpf9x1nn2.js","/_next/static/chunks/1e7h6z92_w2-c.js","/_next/static/chunks/2g-r6rokjl78a.js","/_next/static/chunks/1geiruffics9x.js","/_next/static/chunks/1lfygqrocy8iw.js","/_next/static/chunks/0q47y720ck5-9.js","/_next/static/chunks/03uy_tk5mi4gg.js","/_next/static/chunks/3mi_myijg06x1.js","/_next/static/chunks/2_c926k09c1th.js","/_next/static/chunks/0bvim9_g0hu68.js","/_next/static/chunks/3xav1ddquf5gq.js","/_next/static/chunks/0ayh-bmdnfery.js","/_next/static/chunks/34kl4tv6yifcg.js","/_next/static/chunks/0nm6za7z70maq.js","/_next/static/chunks/44e22u2t839t0.js","/_next/static/chunks/0czpc-f8wjri8.js","/_next/static/chunks/2aq42x9vabhfb.js","/_next/static/chunks/24_gg9g_4g22i.js","/_next/static/chunks/00yjb-caoi49j.js","/_next/static/chunks/1l0z2zsen9vs2.js","/_next/static/chunks/0irw7vnh9fzo0.js","/_next/static/chunks/01auidv8wbc03.js","/_next/static/chunks/434amnen8yqdi.js","/_next/static/chunks/1yd7p-515l2jc.js","/_next/static/chunks/2pqhypz2vo8mu.js","/_next/static/chunks/1i60vi-4s7c4l.js","/_next/static/chunks/2-18150gleij4.js","/_next/static/chunks/295ffwyuqa4b6.js"],"default"] 41:["$","$L44",null,{"hasPartnerEndpoint":false}] 4a:T18f7,# Model Overview ## Description Corrector Diffusion (CorrDiff) US GEFS-HRRR model down-scales several surface and atmospheric variables from 25-km resolution forecast data from the Global Ensemble Forecast System (GEFS) and predicts 3-km resolution High-Resolution Rapid Refresh (HRRR) data. CorrDiff US allows the prediction of high-fidelity stochastic weather phenomena over the CONUS from low-fidelity input data that would otherwise require expensive regional numerical simulations. CorrDiff is a generative downscaling model trained over the contiguous United States (CONUS). This model is ready for commercial use. ## Reference(s) * [CorrDiff Paper](https://arxiv.org/pdf/2309.15214)
* [Codebase](https://github.com/NVIDIA/modulus)
* [Global Ensemble Forecast System](https://www.ncei.noaa.gov/products/weather-climate-models/global-ensemble-forecast)
* [The High-Resolution Rapid Refresh](https://rapidrefresh.noaa.gov/hrrr/)
## Model Architecture **Architecture Type:** Diffusion
**Network Architecture:** Patch-Based Corrector Diffusion
## Input **Input Type(s):** - Tensor (38 Surface & Atmospheric Variables + Forecast Lead Time)
- Input data forecast lead time in hours
**Input Format(s):** NumPy
**Input Parameters:** - Four Dimensional (4D) (batch, variable, latitude, longitude)
- Integer (Lead Time in Hours)
**Other Properties Related to Input:** - 0.25 degree latitude-longitude grid bounded over CONUS - Input resolution: [129, 301] - Lattitude Coordinates: [53, 52.75, 52.5, ..., 21.5, 21.25, 21] - Longitude Coordinates: [225, 225.25, 225.5, ..., 299.5, 299.75, 300] - Input weather variables: "u10m", "v10m", "t2m", "r2m", "sp", "msl","tcwv", "u1000", "u925", "u850", "u700", "u500", "u250", "v1000", "v925", "v850", "v700", "v500", "v250", "z1000", "z925", "z850", "z700", "z500", "z200", "t1000", "t925", "t850", "t700", "t500", "t100", "r1000", "r925", "r850", "r700", "r500", "r100"
## Output **Output Type(s):** Tensor (8 Surface & Atmospheric Variables)
**Output Format:** NumPy
**Output Parameters:** 5D (batch, samples, variable, latitude, longitude)
**Other Properties Related to Output:** - 3-km lambert-conformal projection over CONUS of resolution - Output resolution: [1056, 1792] - Output weather variables: "u10m", "v10m", "t2m", "tp", "csnow", "cicep", "cfrzr", "crain"
The output is on a cropped window of the grid used by HRRR. Refer to the [HRRR documentation](https://rapidrefresh.noaa.gov/hrrr/) for additional information on this grid. The output coordinates can be obtained from the `corrdiff_output_lat.npy` and `corrdiff_output_lon.npy` files in the model package. ## Software Integration **Runtime Engine(s):** Not Applicable
**Supported Hardware Microarchitecture Compatibility:**
* NVIDIA Ampere
* NVIDIA Hopper
* NVIDIA Turing
**Supported Operating System(s):** * Linux
## Model Version(s) **Model version:** v1
# Training, Testing, and Evaluation Datasets: ## Training Dataset **Link:** [GEFS](https://www.ncei.noaa.gov/products/weather-climate-models/global-ensemble-forecast)
*Data Collection Method by dataset*
* Automatic/Sensors
*Labeling Method by dataset*
* Automatic/Sensors
**Properties (Quantity, Dataset Descriptions, Sensor(s)):** GEFS data for the date range of 2020/12/02 to 2023/12/31. The Global Ensemble Forecast System (GEFS) is a weather model created by the National Centers for Environmental Prediction (NCEP) that generates 21 separate forecasts (ensemble members) to address underlying uncertainties in the input data such limited coverage, instruments or observing systems biases, and the limitations of the model itself.
**Link:** [HRRR](https://rapidrefresh.noaa.gov/hrrr/)
*Data Collection Method by dataset*
* Automatic/Sensors
*Labeling Method by dataset*
* Automatic/Sensors
**Properties (Quantity, Dataset Descriptions, Sensor(s)):** HRRR data for the date range of 2020/12/02 to 2023/12/31. The HRRR is a NOAA real-time 3-km resolution, hourly updated, cloud-resolving, convection-allowing atmospheric model, initialized by 3km grids with 3km radar assimilation.
## Evaluation Dataset **Link:** [GEFS](https://www.ncei.noaa.gov/products/weather-climate-models/global-ensemble-forecast)
*Data Collection Method by dataset*
* Automatic/Sensors
*Labeling Method by dataset*
* Automatic/Sensors
**Properties (Quantity, Dataset Descriptions, Sensor(s)):** GEFS data for the date range of 2024/01/01 to 2024/07/31. The Global Ensemble Forecast System (GEFS) is a weather model created by the National Centers for Environmental Prediction (NCEP) that generates 21 separate forecasts (ensemble members) to address underlying uncertainties in the input data such limited coverage, instruments or observing systems biases, and the limitations of the model itself.
**Link:** [HRRR](https://rapidrefresh.noaa.gov/hrrr/)
*Data Collection Method by dataset*
* Automatic/Sensors
*Labeling Method by dataset*
* Automatic/Sensors
**Properties (Quantity, Dataset Descriptions, Sensor(s)):** HRRR data for the date range of 2024/01/01 to 2024/07/31. The HRRR is a NOAA real-time 3-km resolution, hourly updated, cloud-resolving, convection-allowing atmospheric model, initialized by 3km grids with 3km radar assimilation.
# Inference: **Engine:** [Triton](https://developer.nvidia.com/triton-inference-server)
**Test Hardware:** * A100
* H100
* L40S
* RTX6000
## Ethical Considerations: NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their supporting model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards [here](https://ai.nvidia.com). Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).4b:T7b6,Field | Response :------------------------------------------------------------------------------------------------------|:--------------------------------------------------------------------------------- Intended Application & Domain: | Global Weather Forecasting Model Type: | Diffusion Model Intended User: | Climate and Weather scientists accelerating weather prediction with AI. Output: | Downscaled inputs. Describe how the model works: | Diffusion model progressively adds noise to interpolated input to recreate fine-resolution features. Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of: | Not Applicable Technical Limitations: | The model may perform poorly for data sources different from that in the ERA5 training dataset Verified to have met prescribed NVIDIA quality standards: | Yes Performance Metrics: | Accuracy, Throughput and Latency Potential Known Risks: | This model may mispredict fine-resolution features. Licensing: | [Earth-2 Service Terms of Use](https://ngc.nvidia.com/legal/terms)4c:T792,Field | Response :----------------------------------------------------------------------------------------------------------------------------------|:----------------------------------------------- Generatable or reverse engineerable personally-identifiable information (PII)? | None Was consent obtained for any personal data used? | Not Applicable (N/A) Protected class data used to create this model? | None How often is dataset reviewed? | Before Release Is a mechanism in place to honor data subject right of access or deletion of personal data? | N/A If personal data collected for the development of the model, was it collected directly by NVIDIA? | N/A If personal data collected for the development of the model by NVIDIA, do you maintain or have access to disclosures made to data subjects? | N/A If personal data collected for the development of this AI model, was it minimized to only what was required? | N/A Is there provenance for all datasets used in training? | Yes Does data labeling (annotation, metadata) comply with privacy laws? | Yes Is data compliant with data subject requests for data correction or removal, if such a request was made? | N/A4d:T783,#!/usr/bin/env bash if [ "$NGC_API_KEY" = "" ]; then NGC_API_KEY='$NVIDIA_API_KEY' fi invoke_url="https://climate.api.nvidia.com/v1/nvidia/corrdiff" output_file="output.zip" payload='{ "input_id": <%- request.input_id %>, "samples": <%- request.samples %>, "steps": <%- request.steps %> }' echo $payload # Initial request echo "$(date) Making inference request" response=$(curl -D - --request POST -H "content-type: application/json" -H "Authorization: Bearer $NGC_API_KEY" -H "NVCF-POLL-SECONDS: 5" --data "$payload" --location "$invoke_url") http_status=$(echo "$response" | awk '{print $2;exit}') if [ "$http_status" -eq 202 ]; then req_id=$(echo "$response" | grep -i "nvcf-reqid:" | awk '{print $2}' | tr -d '\r') else echo "Unexpected HTTP status: $http_status" echo "Response: $response" exit 1 fi status_url="https://api.nvcf.nvidia.com/v2/nvcf/pexec/status/$req_id" # Poll the /status endpoint echo "$(date) Polling job $req_id" while true; do status_response=$(curl -s -D - --request GET -H "content-type: application/json" -H "Authorization: Bearer $NGC_API_KEY" -H "NVCF-POLL-SECONDS: 5" --location "$status_url" -o "$output_file") status_http_status=$(echo "$status_response" | awk '{print $2;exit}') if [ "$status_http_status" -eq 200 ]; then echo "Saved response to file" break elif [ "$status_http_status" -eq 302 ]; then echo "Downloading large asset" asset_url=$(echo "$status_response" | grep -i "location:" | awk '{print $2}' | tr -d '\r') curl --request GET --location "${asset_url}" -o "${output_file}" break elif [ "$status_http_status" -ne 202 ]; then echo "Unexpected HTTP status: $status_http_status" echo "Response: $status_response" exit 1 fi echo "$(date) Job still running, status $status_http_status" # Wait before polling again sleep 3 done4e:Te3a,package main import ( "bytes" "fmt" "io" "net/http" "os" "time" ) func main() { // Get or request the NGC_API_KEY nvcfRunKey := os.Getenv("NGC_API_KEY") if len(nvcfRunKey) == 0 { nvcfRunKey = "$NVIDIA_API_KEY" } // Define constants and payload invokeURL := "https://climate.api.nvidia.com/v1/nvidia/corrdiff" outputFile := "output.zip" payload := `{"input_id": <%- request.input_id %>, "samples": <%- request.samples %>, "steps": <%- request.steps %>}` fmt.Println("Payload:", payload) // Make initial request fmt.Printf("%s Making inference request\n", time.Now()) req, err := http.NewRequest("POST", invokeURL, bytes.NewBuffer([]byte(payload))) if err != nil { fmt.Println("Error creating request:", err) return } req.Header.Set("Content-Type", "application/json") req.Header.Set("Authorization", "Bearer "+nvcfRunKey) req.Header.Set("NVCF-POLL-SECONDS", "5") client := &http.Client{} resp, err := client.Do(req) if err != nil { fmt.Println("Request error:", err) return } defer resp.Body.Close() // Check HTTP status code if resp.StatusCode != 202 { fmt.Printf("Unexpected HTTP status: %d\n", resp.StatusCode) return } // Get NVCF-ReqID header from response reqID := resp.Header.Get("nvcf-reqid") fmt.Printf("Request ID: %s\n", reqID) // Poll the status endpoint statusURL := fmt.Sprintf("https://api.nvcf.nvidia.com/v2/nvcf/pexec/status/%s", reqID) fmt.Printf("%s Polling job %s\n", time.Now(), reqID) for { statusReq, err := http.NewRequest("GET", statusURL, nil) statusReq.Header.Set("Content-Type", "application/json") statusReq.Header.Set("Authorization", "Bearer "+nvcfRunKey) statusReq.Header.Set("NVCF-POLL-SECONDS", "5") statusResp, err := client.Do(statusReq) if err != nil { fmt.Println("Status request error:", err) return } defer statusResp.Body.Close() // Check status response HTTP code if statusResp.StatusCode == 200 { // Save response to file file, err := os.Create(outputFile) defer file.Close() _, err = io.Copy(file, statusResp.Body) if err != nil { fmt.Println("Error saving response to file:", err) return } fmt.Println("Saved response to file") break } else if statusResp.StatusCode == 302 { // Download large asset from redirected location assetURL := statusResp.Header.Get("Location") fmt.Println("Downloading large asset") assetResp, err := client.Get(assetURL) if err != nil { fmt.Println("Error downloading asset:", err) return } defer assetResp.Body.Close() file, err := os.Create(outputFile) defer file.Close() _, err = io.Copy(file, assetResp.Body) if err != nil { fmt.Println("Error saving asset to file:", err) return } break } else if statusResp.StatusCode != 202 { fmt.Printf("Unexpected HTTP status: %d\n", statusResp.StatusCode) respBody, _ := io.ReadAll(statusResp.Body) fmt.Println("Response:", string(respBody)) return } fmt.Printf("%s Job still running, status %d\n", time.Now(), statusResp.StatusCode) time.Sleep(3 * time.Second) } }4f:T799,#!/usr/bin/env python3 import os import sys import requests import time import logging logging.basicConfig( format='%(asctime)s %(levelname)-8s %(message)s', level=logging.INFO, datefmt='%Y-%m-%d %H:%M:%S') output_file = "output.zip" invoke_url = "https://climate.api.nvidia.com/v1/nvidia/corrdiff" headers = { "Authorization": f"Bearer {os.getenv('NGC_API_KEY', '$NVIDIA_API_KEY')}", "NVCF-POLL-SECONDS": "5" } payload = { "input_id": <%- request.input_id %>, "samples": <%- request.samples %>, "steps": <%- request.steps %>, } # re-use connections session = requests.Session() logging.info(f"Payload {payload}") logging.info("Making inference request") response = session.post(invoke_url, headers=headers, json=payload) response.raise_for_status() if response.status_code == 202: request_id = response.headers['nvcf-reqid'] else: raise Exception("Failed request") logging.info(f"Polling job {request_id}") status_url = f"https://api.nvcf.nvidia.com/v2/nvcf/pexec/status/{request_id}" while(True): response = session.get(status_url, headers=headers, allow_redirects=False) response.raise_for_status() # Invocation is fulfilled. if response.status_code == 200: logging.info(f"Invocation is fulfilled. Downloading to {output_file}") with open(output_file, 'wb') as f: f.write(response.content) break # Large asset response elif response.status_code == 302: logging.info(f"Downloading large asset output to {output_file}") asset_url = response.headers['Location'] with requests.get(asset_url, stream=True) as r: with open(output_file, 'wb') as f: f.write(r.content) break # Response in progress elif response.status_code == 202: logging.info(f"Job still running") else: raise Exception(f"Unexpected status code {response.status_code}") time.sleep(3)50:Tde2,## Step 1. Generate API Key ::generate-api-key ## Step 2. Pull and Run the NIM Pull and run the [NVIDIA Earth-2 CorrDiff NIM](https://catalog.ngc.nvidia.com/orgs/nim/teams/nvidia/containers/corrdiff) with the command below. ```bash docker pull nvcr.io/nim/nvidia/corrdiff:latest ``` This will download the optimized model for your infrastructure. ```bash export NGC_API_KEY= docker run --rm --runtime=nvidia --gpus all --shm-size 4g \ -p 8000:8000 \ -e NGC_API_KEY \ nvcr.io/nim/nvidia/corrdiff:latest ``` ## Step 3. Test the NIM Check the health of the NIM with the following curl command: ```bash curl -X 'GET' \ 'http://localhost:8000/v1/health/ready' \ -H 'accept: application/json' ``` Generate an input numpy array for the model using the following Python script with [Earth2Studio](https://github.com/NVIDIA/earth2studio). See the NVIDIA NIM Docs [quick start guide](https://docs.nvidia.com/nim/earth-2/corrdiff/latest/quickstart-guide.html#fetching-input-data) for more details. ```python from datetime import datetime, timedelta import numpy as np import torch from earth2studio.data import GEFS_FX, GEFS_FX_721x1440 GEFS_SELECT_VARIABLES = ["u10m","v10m","t2m","r2m","sp","msl","tcwv"] GEFS_VARIABLES = ["u1000","u925","u850","u700","u500","u250","v1000","v925","v850",\ "v700","v500","v250","z1000","z925","z850","z700","z500","z200","t1000","t925",\ "t850","t700","t500","t100","r1000","r925","r850","r700","r500","r100"] ds_gefs = GEFS_FX(cache=True) ds_gefs_select = GEFS_FX_721x1440(cache=True, product="gec00") def fetch_input_gefs( time: datetime, lead_time: timedelta, content_dtype: str = "float32" ): dtype = np.dtype(getattr(np, content_dtype)) # Fetch high-res select GEFS input data select_data = ds_gefs_select(time, lead_time, GEFS_SELECT_VARIABLES) select_data = select_data.values # Crop to bounding box [225, 21, 300, 53] select_data = select_data[:, 0, :, 148:277, 900:1201].astype(dtype) assert select_data.shape == (1, len(GEFS_SELECT_VARIABLES), 129, 301) # Fetch GEFS input data pressure_data = ds_gefs(time, lead_time, GEFS_VARIABLES) # Interpolate to 0.25 grid pressure_data = torch.nn.functional.interpolate( torch.Tensor(pressure_data.values), (len(GEFS_VARIABLES), 721, 1440), mode="nearest", ) pressure_data = pressure_data.numpy() # Crop to bounding box [225, 21, 300, 53] pressure_data = pressure_data[:, 0, :, 148:277, 900:1201].astype(dtype) assert pressure_data.shape == (1, len(GEFS_VARIABLES), 129, 301) # Create lead time field lead_hour = int(lead_time.total_seconds() // (3 * 60 * 60)) * np.ones( (1, 1, 129, 301) ).astype(dtype) input_data = np.concatenate([select_data, pressure_data, lead_hour], axis=1)[None] return input_data input_array = fetch_input_gefs(datetime(2023, 1, 1), timedelta(hours=0)) np.save("corrdiff_inputs.npy", input_array) ``` You can now make a local API call using this curl command: ```bash curl -X POST \ -F "input_array=@corrdiff_inputs.npy" \ -F "samples=2" \ -F "steps=12" \ -o output.tar \ http://localhost:8000/v1/infer ``` For more details on getting started with this NIM, visit the [NVIDIA NIM Docs](https://docs.nvidia.com/nim/earth-2/corrdiff/latest/quickstart-guide.html). For more details on the model and its input / output tensors see the [US CorrDiff Model Card](https://catalog.ngc.nvidia.com/orgs/nim/teams/nvidia/models/earth2-corrdiff-us-gefs-hrrr).42:[["$","div",".3",{"className":"relative","children":[["$","div",null,{"className":"relative flex min-h-[194px] w-full flex-col overflow-hidden p-md sm:p-ml bg-manitoulinLightBlack","children":[["$","$L45",null,{"alt":"","className":"object-cover object-center !left-1/2 z-10 !w-1/2 brightness-20 lg:brightness-75","fill":true,"priority":true,"src":"https://assets.ngc.nvidia.com/products/api-catalog/images/corrdiff.jpg","style":{"maskImage":"linear-gradient(to left, rgba(0,0,0,1), rgba(0,0,0,0))"}}],["$","div",null,{"className":"z-30 mx-auto flex w-full max-w-screen-xl min-w-0 flex-1 flex-col items-start justify-between gap-md lg:flex-row lg:gap-ml","children":["$","section",null,{"aria-describedby":"resource-description","aria-labelledby":"resource-name","className":"flex w-full min-w-0 flex-col lg:flex-1","children":["$","div",null,{"className":"flex flex-col gap-1.5 whitespace-pre-wrap","children":[["$","$L46",null,{"className":"w-fit text-ml text-n300 lowercase hover:text-n050","href":"/nvidia","children":"NVIDIA"}],["$","div",null,{"className":"flex flex-col items-start gap-3 lg:flex-row lg:items-center","children":[["$","h1",null,{"className":"max-w-full text-lg leading-heading font-medium break-words text-primary","data-testid":"resource-name","id":"resource-name","children":"corrdiff"}],[["$","span","DEPRECATION",{"className":"nv-badge nv-badge--kind-solid nv-badge--color-red h-[18px] py-0","data-testid":"nv-badge","ref":"$undefined","children":["$undefined","Deprecated"]}],["$","span","AVAILABLE",{"className":"nv-badge nv-badge--kind-solid h-[18px] py-0","data-testid":"nv-badge","ref":"$undefined","children":["$undefined","Downloadable"]}]],"$undefined"]}],["$","p",null,{"className":"max-w-[85ch] text-ms text-primary","id":"resource-description","children":"Generative downscaling model for generating high resolution regional scale weather fields."}],["$","div",null,{"className":"flex w-full flex-col items-start gap-md lg:flex-row lg:items-end lg:justify-between","children":[["$","div",null,{"className":"flex w-full min-w-0 flex-wrap gap-sm lg:flex-1","children":["$","$L47",null,{"artifactType":"ENDPOINT","density":"standard","labels":["AI Weather prediction","Earth-2","nimType:endpoint:nim_type_run_anywhere","usecase:endpoint:usecase_weather_simulation"],"searchRoutePath":"/models"}]}],["$","div",null,{"className":"z-30 flex w-full flex-row justify-start gap-ms sm:justify-end lg:w-auto lg:shrink-0","children":["$undefined",["$","$L48",null,{"cta":{"text":"Self-Host this API","url":"https://enterpriseproductregistration.nvidia.com/?LicType=EVAL&ProductFamily=NVAIEnterprise"},"isNIMAccessRestricted":"$undefined","isNIMAvailable":true}]]}]]}]]}]}]}],["$","div",null,{"className":"pointer-events-none absolute right-0 bottom-0 left-0 z-20 h-30 bg-gradient-to-t to-transparent from-manitoulinLightBlack via-manitoulinLightBlack/70"}]]}],["$","div",null,{"className":"px-4 mx-auto flex max-w-screen-xl flex-col pt-0 lg:px-0","data-body-background":"light-black","children":["$","section",null,{"className":"flex w-full flex-col justify-between rounded-4 border-manitoulinBorderColor bg-manitoulinDarkBlack sm:rounded-6 lg:rounded-8 p-ms lg:p-lg","children":["$","$L49",null,{"artifact":{"artifactType":"ENDPOINT","name":"corrdiff","displayName":"corrdiff","publisher":"nvidia","shortDescription":"Generative downscaling model for generating high resolution regional scale weather fields.","logo":"https://assets.ngc.nvidia.com/products/api-catalog/images/corrdiff.jpg","labels":"$42:0:props:children:0:props:children:1:props:children:props:children:props:children:3:props:children:0:props:children:props:labels","attributes":[{"key":"AVAILABLE","value":"true"},{"key":"DEPRECATION","value":"04/15/2026"}],"updatedDate":"2025-03-22T02:00:11.886Z","bias":"Field | Response\n:---------------------------------------------------------------------------------------------------|:---------------\nParticipation considerations from adversely impacted groups [protected classes](https://www.senate.ca.gov/content/protected-classes) in model design and testing: | None of the Above\nMeasures taken to mitigate against unwanted bias: | None","canGuestDownload":true,"createdDate":"2024-11-18T16:03:37.522Z","description":"$4a","explainability":"$4b","isPublic":true,"isReadOnly":true,"orgName":"qc69jvmznzxy","privacy":"$4c","safetyAndSecurity":"Field | Response\n:---------------------------------------------------|:----------------------------------\nModel Application(s): | Regional Weather Downscaling\nDescribe the life critical impact (if present). | None Known\nUse Case Restrictions: | Abide by [NVIDIA Earth-2 Cloud API Agreement](https://ngc.nvidia.com/legal/terms).\nModel and dataset restrictions: | The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to."},"endpointName":"corrdiff","endpointSpec":{"openAPISpec":{"openapi":"3.0.1","info":{"title":"Earth-2 CorrDiff Preview API","description":"Earth-2 CorrDiff downscaling model preview API. Please see the [Earth-2 home page](https://www.nvidia.com/en-us/high-performance-computing/earth-2/) for more information about Earth-2.\n","version":"1.0.0","termsOfService":"https://www.nvidia.com/en-us/agreements/enterprise-software/product-specific-terms-for-ai-products/","contact":{"name":"NVIDIA Support","url":"https://help.nvidia.com/"},"license":{"name":"NVIDIA Community Model License","url":"https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-community-models-license/"}},"servers":[{"url":"climate.api.nvidia.com/v1"}],"security":[{"Token":[]}],"components":{"securitySchemes":{"Token":{"type":"http","scheme":"bearer"}},"schemas":{"InferenceRequestv1":{"properties":{"input_id":{"type":"integer","maximum":16,"minimum":0,"format":"int32","title":"Input Id","description":"Index indicating sample input data built into the NIM to use","default":1},"samples":{"type":"integer","maximum":4,"minimum":1,"format":"int32","title":"Samples","description":"Number of output samples to generate","default":1},"steps":{"type":"integer","maximum":24,"minimum":1,"format":"int32","title":"Diffusion steps","description":"Number of diffusion steps","default":16},"seed":{"type":"integer","maximum":2147483647,"minimum":0,"format":"int32","title":"Random seed","description":"Random seed that controls the job reproducibility","default":0}},"type":"object","title":"Inference Request"},"InferenceResponse":{"type":"string","format":"binary","example":"Binary stream of\n├─input_u10m.png\n├─output_u10m_000.png\n├─output_u10m_001.png\n├─output_u10m_002.png\n...\n└─output__.png\n","description":"Tar stream containing rendered input (when available) and output fields. Imaged will be precopped to a fixed region over the CONUS in the lon-lat box [230, 295, 23, 52].\n"},"ErrorResponseV1":{"type":"object","properties":{"message":{"type":"string","maxLength":4096,"description":"Error message"}}}}},"paths":{"/v1/infer":{"post":{"summary":"Inference","description":"Run corrdiff inference","operationId":"post_infer","tags":["inference"],"requestBody":{"required":true,"content":{"application/json":{"schema":{"$ref":"#/components/schemas/InferenceRequestv1"}}}},"responses":{"200":{"description":"Successful Response","content":{"application/octet-stream":{"schema":{"$ref":"#/components/schemas/InferenceResponse"}}}},"400":{"description":"Bad inference request","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponseV1"},"example":{"message":"Bad request body"}}}},"500":{"description":"Internal Server Error","content":{"application/json":{"schema":{"$ref":"#/components/schemas/ErrorResponseV1"},"example":{"message":"Internal Triton Server Error"}}}}},"x-nvai-meta":{"name":"CorrDiff United States Downscaling Prediction","returns":"Returns downscaled sample contours for wind speed, temperature, precipitation amount and precipitation type","templates":[{"title":"Synchronous requests","requestEjs":{"shell":"$4d","go":"$4e","python":"$4f"}}]}}}}},"namespace":"qc69jvmznzxy","updatedDate":"2026-04-16T20:29:48.030Z","nvcfFunctionId":"42c1c567-c1c0-49f2-b36b-6587ecc3fcab","createdDate":"2024-11-18T16:03:37.884Z","attributes":{"apiDocsUrl":"https://docs.api.nvidia.com/nim/reference/nvidia-corrdiff","termsOfUse":"GOVERNING TERMS: Your use of this API is governed by the NVIDIA API Trial Service Terms of Use; and the use of this model is governed by the NVIDIA AI Foundation Models Community License.\n","deprecationNotice":"This API will be deprecated on 04/15/2026. It will no longer be supported after 04/15/2026. Please transition to another model to avoid any service interruptions. For more models information, visit our API Reference.","showUnavailableBanner":false,"cta":"$42:0:props:children:0:props:children:1:props:children:props:children:props:children:3:props:children:1:props:children:1:props:cta","deploy":[{"label":"Linux with Docker","filename":"linux.md","contents":"$50"}]},"artifactName":"corrdiff"},"isLoginRequired":true,"playgroundElement":"$undefined","publisherName":"nvidia","searchParams":{},"tabs":[{"label":"Experience","bare":true,"icon":"play","kind":"default","id":"experience","href":"/nvidia/corrdiff","aliases":["/nvidia/corrdiff/experience"]},{"label":"Deploy","kind":"default","id":"deploy","href":"/nvidia/corrdiff/deploy","aliases":"$undefined"}]}]}]}]]}]] 43:["$","$L51",null,{"spec":"$42:0:props:children:1:props:children:props:children:props:endpointSpec"}]