On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

168,932 papers · 148 categories

Trend · papers per month

count % of corpus

6 results for “turbidity”

Short-term prediction of stream turbidity using surrogate data and a meta-model approachstat.ML

Study predicts stream turbidity using surrogate data and meta-model.

problem Costly turbidity sensor deployment limits monitoring networks.

method Dynamic regression (ARIMA), LSTM, GAM models; surrogate covariates (rainfall, water level, temperature, solar exposure); meta-model combining strengths of individual models.

result ARIMA and GAM models with all covariates outperform single models; meta-model yields highest accuracy.

stream turbidity water quality turbidity sensors surrogate data meta-model

2022-10-11abs ↗pdf ↗

Analysis of Hydrological and Suspended Sediment Events from Mad River Watershed using Multivariate Time Series Clusteringcs.LG

New method clusters hydrological and sediment data for storm event analysis.

problem Analyzing storm events for water quality constituents like turbidity.

method Multivariate time series clustering of river discharge and sediment data.

result Clusters differ from 2-D hysteresis loop classifications.

hydrological events sediment transport multivariate clustering Lake Champlain Basin storm analysis

2019-11-28abs ↗pdf ↗

AquaSight: Automatic Water Impurity Detection Utilizing Convolutional Neural Networkscs.LG

AquaSight detects water impurity using deep learning.

problem Water pollution and lack of affordable water quality assessment.

method Convolutional Neural Networks for automated water impurity detection.

result Deep learning model achieved 96% accuracy in detecting water contamination.

water pollution water quality deep learning Convolutional Neural Networks turbidity

2019-07-17abs ↗pdf ↗

Deep Detector Health Management under Adversarial Campaignscs.LG

New method detects adversarial attacks in industrial systems.

problem Adversarial attacks compromise machine learning models in industrial control systems.

method Introduces domain adaptation layer and Monte Carlo simulation for proactive defense.

result Approximates Bayes optimal mitigation for improved detection model health.

Adversarial ML Industrial Control Systems Deep Learning ROC Theory Monte Carlo Simulation

2019-11-19abs ↗pdf ↗

Machine learning regression on hyperspectral data to estimate multiple water parameterscs.CV

In this paper, we present a regression framework involving several machine learning models to estimate water parameters based on hyperspectral data. Measurements from a multi-sensor field campaign, conducted on the River Elbe, Germany, represent the benchmark dataset. It contains hyperspectral data and the five water p…

2018-05-03abs ↗pdf ↗

Time series and machine learning to forecast the water quality from satellite dataphysics.ao-ph

The study forecasts water quality from satellite data using machine learning.

problem Predicting future water quality from satellite data for coastal regions.

method Decomposed time series into components and used machine learning models (SARIMA, regression, neural network).

result Regression and neural network models are best at predicting Chl-a, SARIMA model best at FLH and SST.

water quality satellite data machine learning time series remote sensing

2020-03-16abs ↗pdf ↗