AI Paper Atlas

Research map / Architectures and efficiency / RNNs and normalization

AirDelhi: Fine-Grained Spatio-Temporal Particulate Matter Dataset From Delhi For ML based Modeling

Sachin Chauhan, Zeel Bharatkumar Patel, Sayan Ranu, Rijurekha Sen, Nipun Batra

NeurIPS 2023 · Architectures and efficiency › RNNs and normalization · approach: Dataset distillation and data-efficient training · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
normalize time separately for each day instead of across days (ablation)Random Forest · Delhi (Day) forecastingtest RMSE: 110.49 -> 89.54Improved
normalize time separately for each day instead of across days (ablation)XGBoost · Delhi (Day) forecastingtest RMSE: 102.68 -> 84.15Improved
normalize time separately for each day instead of across days (ablation)NSGP · Delhi (Day) forecastingtest RMSE: 95.83 -> 86.34Improved
normalize time separately for each day instead of across days (ablation)IDW · Delhi (Day) forecastingtest RMSE: 86.52 -> 270.73Hurt
use learned ML models instead of the Mean PredictorRandom Forest · Delhi (Day) interpolationRMSE: 65.80 -> 22.24Improved
use distance weighting (IDW) instead of Mean PredictorIDW · Delhi (Day) interpolationRMSE improvement: 39.3%Improved
drop training-day data and use only test-day visible set (ACT to C) (ablation)XGBoost · Delhi (Day) interpolationRMSE: 33.24 -> 29.73Improved
drop training-day data and use only test-day visible set (ACT to C) (ablation)Random Forest · Delhi (Day) interpolationRMSE: 22.24 -> 22.24No clear effect
drop historical training days (ablation)NSGP · Delhi (Day) interpolationRMSEHurt
use recent complex models (NSGP, GraphSage, N-BEATS) instead of Random Forest/XGBoostNSGP, GraphSage, N-BEATS · Delhi (Day)RMSENo clear effect
switch task from interpolation to forecastingbest model · Delhi (Day)RMSE: 22.24 -> 84.15Hurt
evaluate on Delhi data versus Canada/USA dataML models vs Mean Predictor · PM2.5 datasetsRMSE improvement over Mean Predictor: Canada ~27% best, USA 16% - 26%, Delhi up to 66.2%Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy