Pith. sign in

REVIEW 9 cited by

Quantum-Train Long Short-Term Memory: Application on Flood Prediction Problem

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2407.08617 v1 pith:6QKTCATY submitted 2024-07-11 quant-ph

classification quant-ph
keywords floodquantumclassicalparameterspredictionchallengelongmemory
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Flood prediction is a critical challenge in the context of climate change, with significant implications for ecosystem preservation, human safety, and infrastructure protection. In this study, we tackle this problem by applying the Quantum-Train (QT) technique to a forecasting Long Short-Term Memory (LSTM) model trained by Quantum Machine Learning (QML) with significant parameter reduction. The QT technique, originally successful in the A Matter of Taste challenge at QHack 2024, leverages QML to reduce the number of trainable parameters to a polylogarithmic function of the number of parameters in a classical neural network (NN). This innovative framework maps classical NN weights to a Hilbert space, altering quantum state probability distributions to adjust NN parameters. Our approach directly processes classical data without the need for quantum embedding and operates independently of quantum computing resources post-training, making it highly practical and accessible for real-world flood prediction applications. This model aims to improve the efficiency of flood forecasts, ultimately contributing to better disaster preparedness and response.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 9 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Transfer Learning Analysis of Variational Quantum Circuits

    quant-ph 2025-01 reject novelty 5.0 of 10

    The paper derives an analytical one-shot parameter update for variational quantum circuits under small domain shifts and tests it on a two-moons classification task.

  2. Learning to Program Quantum Measurements for Machine Learning

    quant-ph 2025-05 conditional novelty 4.0 of 10

    A neural network that generates data-conditioned Hermitian observables for variational quantum circuits yields improved classification accuracy and training stability on synthetic benchmarks.

  3. Quantum-Train-Based Distributed Multi-Agent Reinforcement Learning

    quant-ph 2024-12 reject novelty 4.0 of 10

    A quantum parameter-generating circuit combined with gradient averaging across agents reaches a target reward in fewer episodes than a single-agent version on MiniGrid Empty-5x5-v0.

  4. Programming Variational Quantum Circuits with Quantum-Train Agent

    quant-ph 2024-12 conditional novelty 4.0 of 10

    A hybrid quantum-classical architecture uses Quantum-Train to compress the slow programmer of a Quantum Fast Weight Programmer, cutting trainable parameters by 70-90% on time-series benchmarks.

  5. Quantum Kernel-Based Long Short-term Memory

    quant-ph 2024-11 reject novelty 4.0 of 10

    QK-LSTM replaces LSTM gate linear transforms with quantum kernel sums, but its claimed accuracy parity rests on a two-sentence training-only example.

  6. Quantum Feature Optimization for Enhanced Clustering of Blockchain Transaction Data

    cs.LG 2025-05 reject novelty 3.0 of 10

    Quantum feature maps are reported to improve blockchain transaction clustering, but the comparison omits classical random features and the results are selected on the test set.

  7. Quantum Kernel-Based Long Short-term Memory for Climate Time-Series Forecasting

    quant-ph 2024-12 reject novelty 3.0 of 10

    A quantum kernel-based LSTM reports 42% lower RMSE than a classical LSTM on one AQI forecasting benchmark, with far fewer parameters.

  8. Predicting Water Quality using Quantum Machine Learning: The Case of the Umgeni Catchment (U20A) Study Region

    quant-ph 2024-11 reject novelty 3.0 of 10

    On a 32-point water quality dataset from Durban, a quantum support vector classifier reached 75% accuracy while a quantum neural network consistently failed to train.

  9. Introduction to Quantum Machine Learning and Quantum Architecture Search

    quant-ph 2025-04 unverdicted novelty 1.0 of 10

    A tutorial reviewing quantum machine learning models and automated quantum architecture search methods, with no new experiments or derivations.

Pith tools