Detection & Monitoring the Water Pollutants Using Light Detection & Ranging

1
3RD
INTERNATIONAL CONFERENCE ON OPTIMIZATION
TECHNIQUES IN THE FIELD OF ENGINEERING (ICOFE-2024)
289-Detection & Monitoring the Water Pollutants Using Light Detection &
Ranging
22nd
And 23rd
Oct 2024 3RD
International Conference on Optimization Techniques in the Field of Engineering ICOFE-2024
AUTHORS NAME
1. MOHAMED RIDWAN NISATH S
2. MOHAMMED NABEEL
3. MOTA HARSHAVARDHAN REDDY
4. N.SIVAKUMAR
KSR College Of Engineering , Nammakal , Tamil Nadu, India
&
Debre Tabor University Ethiopia
22nd
And 23rd
Oct 2024
Corresponding Author Affiliation Details: MOHAMED RIDWAN NISATH S
UG Student, Department of Artificial Intelligence and Data Science, Panimalar Engineering College, Chennai, 600123
Email: smortridwan@gmail.com

2
TABLE OF CONTENTS
22nd
And 23rd
Oct 2024 3RD
 Introduction
 Problem Statement
 Literature Review/Related Work
 Research Methodology
 System Architecture/Design
 Experimental Setup
 Results
 Conclusion
 Future Work
 Acknowledgments
 References

3
22nd
And 23rd
Oct 2024 3RD
INTRODUCTION
 Water pollution is a critical global environmental issue requiring efficient
solutions.
 LiDAR technology is utilized for precise 3D surface mapping and accurate water
quality assessment.
 Folium is integrated for advanced geospatial visualization, enabling identification
of pollution hotspots.
 This method enables real-time monitoring and rapid evaluation of water quality,
surpassing traditional methods.
 The research highlights the role of cutting-edge technologies in timely pollution
detection and environmental conservation.

4
22nd
And 23rd
Oct 2024 3RD
PROBLEM STATEMENT
 Current water quality assessment methods are often slow and lack
accuracy, hindering effective monitoring and management of
pollution. A more efficient solution is required for real-time
detection and evaluation of water pollution .

5
22nd
And 23rd
Oct 2024 3RD
LITERATURE REVIEW
Title Author(s) Year Cons
The role of remote sensing
in the evolution of water
pollution detection and
monitoring
Gordana Kaplan, Fatma
Yalcinkaya, Esra Altıok,
Andrea Pietrelli, Rosa Anna
Nastro, Nicola Lovecchio
2023 Can cause information
overload, complicating
relevant detail extraction.
Interpolation of airborne
LiDAR data for
archaeology
Lozić, Edisa & Eichert, Stefan
& Štular, Benjamin
2023 Computational intensity, data
sparsity, accuracy trade-offs,
and processing time.
High-Density and Low-
Crosstalk Multilayer
Silicon Nitride Waveguide
Superlattices with Air Gaps
Li, Wenling & Liu, Jing-wei &
Cheng, Guo-an & Zheng, Rui-
ting & Wu, Xiao-ling
2023 Complex fabrication,
sensitivity to variations,
limited operational wavelength
range.

6
22nd
And 23rd
Oct 2024 3RD
LITERATURE REVIEW
Title Author(s) Year Cons
Evaluating the
Archaeological Efficacy of
Bathymetric LiDAR across
Oceanographic Contexts
Cook Hale, Jessica & Davis,
Dylan & Sanger, Matthew
2023 Environmental factors, high
sedimentation impacts, limited
underwater visibility,
technology adaptation.
A Simultaneous Pipe-
Attribute and PIG-Pose
Estimation (SPPE) Using
3-D Point Cloud in
Compressible Gas
Pipelines
Hung, Nguyen & Park, Jae-
Hyun & Jeong, Han-You.
2023 Complex optimization,
dependency on sensor
accuracy, requires extensive
calibration.
Solar Potential Uncertainty
in Building Rooftops as a
Function of Digital Surface
Model Accuracy
Polo, Jesus & García, Redlich 2023 High uncertainty in DSM
accuracy, complex topography
issues, variable measurement
reliability.

7
22nd
And 23rd
Oct 2024 3RD
RESEARCH METHODOLOGY
STEP 1: Data Collection & Sampling Techniques
 Microplastic Data Collection:
Data on microplastics were gathered from various environmental samples, such as water and
sediment, across different regions. A laboratory method was employed, involving filtering,
separating, drying, and weighing samples to quantify the amount of microplastic debris
present.
 Interlaboratory Comparison:
Identical water samples containing known quantities of microplastics were distributed to
different laboratories. Each lab utilized its own procedures for filtering and isolating
microplastics. The resulting data were compared to evaluate the consistency and reliability of
the methodologies employed by each laboratory.

8
22nd
And 23rd
Oct 2024 3RD
STEP 2: Data Analysis & Visualization
 Libraries and Packages: Various Python libraries were used for data analysis, such as
pandas for data manipulation, seaborn and matplotlib for visualizations, folium for
geospatial mapping, and scipy for scientific computations. These tools enabled an in-depth
exploration of trends, anomalies, and correlations within the datasets.
 Data Sources:
SEA_MICRO.csv: A dataset containing latitude, longitude, and microplastic density
(Pieces per KM²) over time.
GEO_READING.csv: Data on microplastic concentration (particles per cubic meter)
from marine locations.
ADVENTURE_MICRO_FROM_SCIENTIST.csv: Contributions from adventure
scientists, mapping the presence of microplastics over different dates and locations.
 Geospatial Mapping: The use of the folium library and its plugins allowed the visualization
of microplastic concentrations across different geographic locations. Heatmaps and marker
clusters were created to visually represent areas with higher densities of microplastics,
making it easier to identify pollution hotspots.

9
22nd
And 23rd
Oct 2024 3RD
STEP 3: Interlaboratory Data Comparison
 The interlaboratory comparison involved sending identical reference samples to six
laboratories, allowing researchers to compare results. Differences in results (e.g., in
microplastic concentrations) were then evaluated against the known values in the reference
samples, assessing each lab's accuracy and consistency.
STEP 4: Output & Results
 Visualizing Trends: Time-series plots using plotly and matplotlib provided insights into
changes in microplastic concentration over time. These visualizations helped identify
spikes in microplastic density, such as the highest value of 12,316,946 pieces per KM²
recorded on October 16, 2012.
 Geospatial Heatmaps: The folium library was used to generate heatmaps, pinpointing
regions with the highest microplastic concentrations, e.g., locations around 21.507712° N,
119.547692° E were found to have the highest concentration of microplastic particles per
cubic meter.

10
22nd
And 23rd
Oct 2024 3RD
Methodology Summary
 Data Collection: Environmental samples were collected, processed, and quantified using
standardized and laboratory-specific methods.
 Geospatial and Temporal Analysis: Microplastic densities were mapped over time and
location using Python data visualization libraries.
 Comparative Analysis: Interlaboratory comparison results were examined for discrepancies
to promote global standardization in sampling protocols.

11
22nd
And 23rd
Oct 2024 3RD
FLOWCHART/DESIGN

12
22nd
And 23rd
Oct 2024 3RD
 Experimental Design
Reference Sample Creation: Prepare samples with known concentrations of
microplastics and organic matter.
Distribution: Mail reference samples to selected laboratories (6 national and
international) with established expertise in microplastic research.
Data Collection: Each laboratory will use their own protocols to analyze the
samples and report the results.
 Analysis Parameters
Quantification of Microplastics: Count and weigh the isolated microplastics.
Comparative Analysis: Compare the results obtained by different laboratories with
the known concentrations in the reference samples.
EXPERIMENTAL SETUP

13
22nd
And 23rd
Oct 2024 3RD
 Data Analysis Methods
Use pandas for data manipulation and analysis. Visualize results using matplotlib and
plotly for graphical representation. Conduct statistical analysis to assess the variability and
reliability of results.
 Packages and Libraries Required
import pandas as pd, import matplotlib.pyplot as plt, import plotly.express as px, import
folium, from folium import plugins, import seaborn as sns.
 Data Visualization and Interpretation
Data Input: Read and process datasets (CSV files) containing microplastic concentration
and geographic information.
Geospatial Analysis:
• Create maps visualizing the distribution of microplastics using folium.
• Implement heatmaps to illustrate areas with higher concentrations of microplastics.
Time Series Analysis: Use line plots to depict trends in microplastic concentration over
time.

14
22nd
And 23rd
Oct 2024 3RD
 Our research on microplastic sampling protocols revealed significant findings that enhance our
understanding of microplastic distribution across various environments. By standardizing sampling
techniques, we ensured the comparability of results across laboratories, ultimately facilitating a more
accurate assessment of microplastic pollution.
 These insights are crucial for informing effective environmental policies and strategies. Additionally,
our approach can significantly improve monitoring efforts and contribute to the development of
sustainable practices aimed at mitigating the impacts of microplastics in ecosystems.
RESULTS

15
22nd
And 23rd
Oct 2024 3RD
This study demonstrates the effectiveness of LiDAR technology in conducting detailed
topographic surveys of American coastal regions. By capturing high-resolution, three-
dimensional data, LiDAR facilitates the creation of Digital Elevation Models (DEMs) and
other visual outputs, providing precise representations of coastal landscapes.
The extracted parameters, such as elevation, slope, and aspect, offer valuable quantitative
insights for coastal terrain analysis. The centimeter-level precision of the data enhances its
reliability, making LiDAR an indispensable tool for coastal science. This approach
significantly contributes to coastal management, environmental planning, and disaster
management, enabling stakeholders to make informed decisions based on accurate terrain
assessments.
CONCLUSIONS

16
22nd
And 23rd
Oct 2024 3RD
Automated Sampling and Analysis Tools
 Robotic Sample Collection : Develop autonomous underwater vehicles (AUVs) equipped
with sensors and sampling equipment to collect water samples from various depths and
locations.
 Image Recognition for Microplastics: Implement machine learning algorithms using
image recognition to automatically identify and classify microplastic types from collected
samples.
Standardized Database for Microplastic Data
 Centralized Data Repository: Create a global database where researchers can upload their
microplastic data, including methods, results, and sampling conditions. This would
facilitate better comparisons and analyses.
 Open Access: Ensure that the database is accessible to all researchers and policymakers to
promote transparency and collaboration.
FUTURE WORK

17
22nd
And 23rd
Oct 2024 3RD
Research Team:
 I would like to thank my teammates for their valuable contributions and support
throughout this research project.
 Institution Support:
 A special thanks to Panimalar Engineering College for providing an encouraging
environment for research and collaboration.
 Personal Gratitude:
 I appreciate the guidance and insights from my professors and mentors who helped
shape this project.
ACKNOWLEDGMENTS

18
22nd
And 23rd
Oct 2024 3RD
 Gordana Kaplan, Fatma Yalcinkaya, Esra Altıok, Andrea Pietrelli, Rosa Anna Nastro,
Nicola Lovecchio, Ioannis A. Ieropoulos, Argyro Tsipa, The role of remote sensing in the
evolution of water pollution detection and monitoring: A comprehensive review, Physics
and Chemistry of the Earth, Parts A/B/C, Volume 136, 2024, 103712, ISSN 1474-7065.
 Lozić, Edisa & Eichert, Stefan & Štular, Benjamin. (2023). Interpolation of airborne
LiDAR data for archaeology. Journal of Archaeological Science: Reports. 48.103840.
10.1016/j.jasrep.2023.103840
 Li, Wenling & Liu, Jing-wei & Cheng, Guo-an & Zheng, Rui-ting & Wu, Xiao-ling.
(2023). High-Density and Low-Crosstalk Multilayer Silicon Nitride Waveguide
Superlattices with Air Gaps. IEEE Photonics Journal. 15. 1-8.
10.1109/JPHOT.2022.3232094.
 Cook Hale, Jessica & Davis, Dylan & Sanger, Matthew. (2023). Evaluating the
Archaeological Efficacy of Bathymetric LiDAR across Oceanographic Contexts: A Case
Study from Apalachee Bay, Florida. Heritage. 6. 928-945. 10.3390/heritage6020051.
REFERENCES

19
22nd
And 23rd
Oct 2024 3RD
 Hung, Nguyen & Park, Jae-Hyun & Jeong, Han-You. (2023). A Simultaneous Pipe-
Attribute and PIG-Pose Estimation (SPPE) Using 3-D Point Cloud in Compressible Gas
Pipelines. Sensors. 23. 1196. 10.3390/s23031196.
 Polo, Jesus & García, Redlich. (2023). Solar Potential Uncertainty in Building Rooftops as
a Function of Digital Surface Model Accuracy. Remote Sensing. 15. 567.
10.3390/rs15030567.
 Ze-hou Yang, Yong-ke Zhang, Yong Chen, Xiao-feng Li, Yong Jiang, Zhen-zhong Feng, Bo
Deng, Chun-li Chen, Ding-fu Zhou, Simultaneous detection of multiple gaseous pollutants
using multi-wavelength differential absorption LIDAR, Optics Communications, Volume
518, 2022, 128359, ISSN 0030-4018.
 Nina Gnann, Björn Baschek, Thomas A. Ternes, Close-range remote sensing-based
detection and identification of microplastics on water assisted by artificial intelligence: A
review, Water Research, Volume 222, 2022, 118902, ISSN 0043-1354.
 Yang, H.; Kong, J.; Hu, H.; Du, Y.; Gao, M.; Chen, F. A Review of Remote Sensing for
Water Quality Retrieval: Progress and Challenges. Remote Sens. 2022, 14, 1770.

20
22nd
And 23rd
Oct 2024 3RD
 Nur Hanis Hayati Hairom, Chin Fhong Soon, Radin Maya Saphira Radin Mohamed,
Marlia Morsin, Nurfarina Zainal, Nafarizal Nayan, Che Zalina Zulkifli, Nor Hazlyna
Harun, A review of nanotechnological applications to detect and control surface water
pollution, Environmental Technology & Innovation, Volume 24, 2021, 102032, ISSN 2352-
1864.
 Georgios Zamanakos, Lazaros Tsochatzidis, Angelos Amanatiadis, Ioannis Pratikakis, A
comprehensive survey of LiDAR-based 3D object detection methods with deep learning
for autonomous driving, Computers & Graphics, Volume 99,PP 153-181, 2021.
 Yu-Cheng Fan, Chitra Meghala Yelamandala, Ting-Wei Chen, Chun-Ju Huang, "Real-Time
Object Detection for LiDAR Based on LS-R-YOLOv4 Neural Network", Journal of
Sensors, vol. 2021, Article ID 5576262,11 pages, 2021.
 Muro, S., Yoshida, I., Hashimoto, M. et al. Moving-object detection and tracking by
scanning LiDAR mounted on motorcycle based on dynamic background subtraction. Artif
Life Robotics 26, 412–422 (2021).
 [15] Prosposito, P.; Burratti, L.; Venditti, I. Silver Nanoparticles as Colorimetric Sensors
for Water Pollutants. Chemosensors 2020, 8, 26.

Detection & Monitoring the Water Pollutants Using Light Detection & Ranging

More Related Content

Similar to Detection & Monitoring the Water Pollutants Using Light Detection & Ranging (20)

Recently uploaded (20)

Detection & Monitoring the Water Pollutants Using Light Detection & Ranging