SHSoheyl Faghir Hagh

Soheyl Faghir Hagh

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Soheyl Faghir Hagh has a total of 34 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Internet of Drones System for Real-Time Wireless Water Quality Sensing, 2-D Mapping, 3-D Depth Profiling, and Intelligent Sampling

    by Soheyl Faghir Hagh, Parmida Amngostar, Dylan Burns, Renato Figueiredo, Yun-Jung Ku, Jacob Cianci-Gaskill, Steven E. McMurray, Dryver Huston, Tian Xia


  • Embedded IoT System for Acoustic Precipitation Phase Partitioning via Edge ML and MFCCs

    by Soheyl Faghir Hagh, Jordan Bourdeau, Julia Sober, Rachael Chertok, Christopher Jepsen, Parmida Amngostar, Lucas Levine, Casey Forey, Tian Xia, Christian Skalka

    Accurate and real-time detection of precipitation phases is essential for hydrological modeling, water resource management, and climate impact assessments. However, conventional methods struggle to distinguish precipitation phase near freezing and are unsuitable for distributed deployment in remote, complex terrain due to cost, size, and power constraints. In this work, we present an integrated acoustic sensing system that combines machine learning (ML) on the edge with acoustic sensing and Mel-frequency cepstral coefficients (MFCCs)-based feature extraction, all implemented on our designed edge device. The device is low-cost, with LAN and WAN capabilities for near real-time reporting and can integrate multiple sensors for snow hydrology studies, in addition to detecting the precipitation phase. We present the design, fabrication, and validation of the Advanced Unified Rainfall and Atmospheric Monitoring (AURA) system, integrating sensors for temperature, humidity, ultrasonic snow depth, solar radiation, and wind velocity. AURA features an embedded ML algorithm that enables accurate classification of precipitation phases. Short-time Fourier Transform (STFT) and MFCCs are computed on the edge from recorded precipitation acoustics via novel Mel filter bank computation methods. Using support vector machine (SVM) and random forest (RF) classifiers, the RF model achieves testing accuracy of 97.35% on simulated precipitation acoustics and 85.67% in consolidated class (CC) environmental recordings. The SVM classifier achieves 98.07% accuracy on simulated acoustics and 85.99% on CC environmental recordings. The low-power AURA network uses a long range (LoRa) star topology with time-division multiple access (TDMA) and an Iridium gateway for reliable data transfer from remote sites. Signal-to-noise ratio (SNR) analysis and comprehensive field tests confirm and validate system performance.


  • Open Access

    Embedded IoT System for Acoustic Precipitation Phase Partitioning via Edge ML and MFCCs

    by Soheyl Faghir Hagh, Jordan Bourdeau, Julia Sober, Rachael Chertok, Christopher Jepsen, Parmida Amngostar, Lucas Levine, Casey Forey, Christian Skalka, Tian Xia

    Accurate and real-time detection of precipitation phases is essential for hydrological modeling, water resource management, and climate impact assessments. However, conventional methods struggle to distinguish precipitation phase near freezing and are unsuitable for distributed deployment in remote, complex terrain due to cost, size, and power constraints. In this work, we present an integrated acoustic sensing system that combines machine learning on the edge with acoustic sensing and Mel-Frequency Cepstral Coefficients (MFCC)-based feature extraction, all implemented on our designed edge device. The device is low-cost, with LAN and WAN capabilities for near real-time reporting, and can integrate multiple sensors for snow hydrology studies, in addition to precipitation phase detection. We present the design, fabrication, and validation of the Advanced Unified Rainfall and Atmospheric Monitoring (AURA) system, integrating sensors for temperature, humidity, ultrasonic snow depth, solar radiation, and wind velocity. AURA features an embedded machine learning algorithm to enable accurate classification of precipitation phases. Short-time Fourier Transform (STFT) and MFCCs are computed on each sensor node from recorded precipitation acoustics employing two novel Mel filter bank computation methods: a lookup table and a linear model. Using support vector machine (SVM) and random forest (RF) classifiers, the RF model achieves testing accuracy of 97.35% on simulated precipitation acoustics and 85.67% in consolidated class (CC) environmental recordings. The SVM classifier achieves 98.07% accuracy on simulated acoustics and 85.99% on CC environmental recordings. The low-power AURA network employs a LoRa star topology with Time-Division Multiple Access (TDMA) and an Iridium-enabled gateway for reliable data transmission from remote, offline locations. Field testing and ground-truth validation confirm system reliability.

  • LoRaStat: A Low-Cost Portable LoRaWAN Potentiostat for Wireless and Real-Time Monitoring of Water Quality and Pollution

    by Parmida Amngostar, Monireh Dehabadi, Soheyl Faghir Hagh, Appala Raju Badireddy, Dryver Huston, Tian Xia

    This paper presents a low-power, portable potentiostat integrating the wireless communication of the Long-Range Wide Area Network. This device provides a cost-effective solution for conducting electrochemical measurements of ammonium (NH 4 + ), nitrate (NO 3 - ), and calcium (Ca 2+ ) levels in aqueous environment. Additionally, the system is equipped with supplemental sensors to monitor the temperature and moisture of the medium, facilitating more comprehensive sensing and compensation. Furthermore, this potentiostat enables multiple electrochemical techniques, such as Cyclic Voltammetry and Zero Current Potentiometry, to analyze different analytes’ redox behavior. The system can perform in-sensor local data analysis to improve sensing efficiency. By optimizing power consumption, the system can perform continuous sensing for over a month, making it suitable for long-term monitoring. The ability to precisely and quickly measure a wide current range spanning from 15 nA to 15 mA facilitates tracking of analyte concentration variations, thereby enabling the detection of even minor changes. A comprehensive comparison between our system and a commercial Metrohm potentiostat under various conditions validates the reliability and performance of LoRaStat.


  • LoRa Pore Pressure Probe for Real-Time Coastal Environment Monitoring

    by Soheyl Faghir Hagh, Parmida Amngostar, Dylan Burns, Saba Molaei, Aaron Gallant, Dryver Huston, Tian Xia

    Pore pressure monitoring in soil is used to understand subsurface hydrodynamics and the influence of infiltration and exfiltration processes influencing beach erosion and morphology in sandy soils. In this work, we develop a low-power, multi-sensor, long-range wireless probe applicable for short-time, frequent, real-time monitoring of pore pressure and coastal environments at various soil depths. The probe features eight pressure and temperature sensors aligned vertically on a copper pipe at different depths from the soil surface to resolve hydraulic gradients influencing sediment stability. The LoRa sensor probe features data compression and real-time data transmission for faster transmission. The sampling frequency of the developed instrument is variable to capture rapid dynamic variations in pressure according to environmental conditions. The device in this work logs the collected data onto an SD card locally in addition to wireless transmission. The fabricated waterproof probe is tested and calibrated in the laboratory using a water container at different water heights, with minor sensor-to-sensor variations. Comprehensive field tests indicate a promising wave event detection and wireless pore pressure monitoring platform suitable for various soil types, including heterogeneous soils.


  • Open Access

    A Low-Cost LoRa Optical Fluorometer–Nephelometer for Wireless Monitoring of Water Quality Parameters in Real Time

    by Soheyl Faghir Hagh, Parmida Amngostar, Wenzhe Chen, Jessica Sheridan, Clayton J. Williams, Ana M. Morales-Williams, Dryver Huston, Tian Xia

    Real-time monitoring of water quality parameters using optical sensors has become widespread. However, the price of commercial sensors and the ability to integrate them into customized sensing networks can limit their application in research and monitoring programs. This study introduces the design, verification, and validation of an innovative, low-cost, portable, low-power fluorometer-nephelometer device, employing Long-Range Wide Area Network technology. The developed Internet of Things capable device can measure temperature, turbidity, phycocyanin fluorescence (a proxy for cyanobacteria biomass), and chlorophyll- a fluorescence (a proxy for phytoplankton (cyanobacteria plus algae) biomass) in aquatic ecosystems. The fluorometer-nephelometer structure employs one digital thermistor probe, three distinct light-emitting diodes (LEDs) that are amber (590 nm) to excite phycocyanin pigments of cyanobacteria, blue (465 nm) to excite chlorophyll- a pigments of phytoplankton, and near-infrared (870 nm) to measure turbidity through light scattering. Two orthogonal silicon photodiodes are used as detectors set in line with long pass filters of 830 nm for turbidity and 630 nm for phytoplankton. A peristaltic pump circulates water through a polymethylmethacrylate cuvette within a 3D-printed fluorometer assembled in a weatherproof box. The activation by personalization LoRaWAN protocol is utilized for real-time wireless transmission of water quality data while a micro-SD card is employed for storing the data locally. The optical sensor tests are conducted in the laboratory using standard turbidity solutions and pigments. The turbidity, phycocyanin, and chlorophyll-a sensing ranges are 3-200 FTU, 0.025-2.5 mg-PC/L, and 1-50 μg-chl/L, respectively. In repeated laboratory tests, the relative percent difference is consistently less than 10%.


  • Autonomous UAV-Mounted LoRaWAN System for Real-Time Monitoring of Harmful Algal Blooms (HABs) and Water Quality

    by Soheyl Faghir Hagh, Parmida Amngostar, Adam Zylka, Maddy Zimmerman, Lauren Cresanti, Spencer Karins, Jarlath Patrick O’neil-Dunne, Koa Ritz, Clayton J. Williams, Ana M. Morales-Williams, et al.

    Harmful algal blooms (HABs) frequently occur in coastal and inland water bodies, resulting in detrimental health and economic consequences. In freshwater, HABs are often dominated by cyanobacteria (CyanoHABs or cHABs), which produce a suite of secondary metabolites ranging from taste and odor compounds to liver and neurological toxins. Recently, Uncrewed Aerial Vehicles (UAVs) have emerged as a cost-effective remote sensing solution for using imaging cameras to monitor the distribution of HABs. However, most of these systems are unable to concurrently measure crucial water parameters, requiring additional in situ measurements and sample collection. The UAV system developed in this work presents a comprehensive platform that integrates multiple water sensors, including near-infrared (NIR) multispectral cameras and temperature, pH, and turbidity sensors. The integrated sensor system can not only monitor HAB distributions but also measure essential water quality parameters. In addition, the electromechanical 3D-printed water sampling structure is designed to collect water samples for laboratory analysis of chemical and biological samples. To ensure real-time data transmission, a Long-Range Wide Area Network (LoRaWAN) is developed. An ArcGIS database is implemented for water quality and HAB distribution mapping. Comprehensive field tests have been performed for system performance validation and assessment.