AI Paper Atlas

Research map / Time series / Long-term forecasting

Multi-Horizon Time Series Forecasting of Non-Parametric CDFs with Deep Lattice Networks

Niklas Erdmann, Lars Bentsen, Roy Stenbro, Heine Nygard Riise, Narada Dilp Warakagoda, Paal E. Engelstad

AAAI 2026 · Time series › Long-term forecasting · approach: Lightweight long-term forecasters · 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
constrain quantile monotonicity with a DLN instead of an unconstrained NN output (ablation)SQR LSTM forecaster · Solar irradiance day-aheadMAE / RMSE: MAE 42.612 -> 43.266; RMSE 72.930 -> 74.520No clear effect
use DLN instead of unconstrained NN output (ablation)SQR LSTM forecaster · Solar irradiance day-aheadACE: 0.075 -> 0.061Improved
use DLN instead of unconstrained NN output (ablation)SQR LSTM forecaster · Solar irradiance day-aheadCRPS: 27.690 -> 29.175Hurt
use DLN instead of SMNN as monotonic output model (ablation)SQR LSTM forecaster · Solar irradiance day-aheadMAE: 47.548 -> 43.266Improved
use DLN instead of SMNN (ablation)SQR LSTM forecaster · Solar irradiance day-aheadCRPS / ACE: CRPS 29.333 -> 29.175No clear effect
use non-linear DLN instead of linear output layer (ablation)SQR LSTM forecaster · Solar irradiance day-aheadACE: 0.173 -> 0.061Improved
use non-linear DLN instead of linear output layer (ablation)SQR LSTM forecaster · Solar irradiance day-aheadCRPS: 24.427 -> 29.175Hurt
use constrained linear output instead of linear (ablation)SQR LSTM forecaster · Solar irradiance day-aheadACE: 0.173 -> 0.190No clear effect
SQR with DLN instead of QR with 11 fixed quantilesLSTM forecaster · Solar irradiance day-aheadACE: 0.052 -> 0.061; CRPS 30.506 -> 29.175Mixed
SQR probabilistic training instead of point predictionLSTM forecaster · Solar irradiance day-aheadRMSE: 74.933 -> 72.930 (LSTM-NN)Improved
use LSTM-DLN instead of smart persistenceLSTM-DLN · Solar irradiance day-aheadMAE: 52.903 -> 43.266Improved
constrain with DLN to prevent quantile crossoverSQR LSTM forecaster · Solar irradiance day-aheadquantile crossover: 3.075 % -> 0 (guaranteed monotonic)Improved

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