// ACADEMIC CONTENT PORTAL · Engineering

Thesis Topic Ideas: Air Quality Monitoring and Prediction in Kathmandu Valley

Level: Bachelor, MasterDifficulty: Intermediate

Applicable Universities:Kathmandu University (KU)Tribhuvan University (TU)Pokhara University (PU)University of CambridgeUniversity of Oxford

🎓 Academic Journey Progression Map

Grade 8-10 (SEE)
School Projects
+2 (Grades 11-12)
Stream Projects
Bachelor's Degree
Undergraduate Thesis
Master's Degree
Postgraduate Thesis
PhD Doctorate
Dissertation Guidance

1. Introduction & Problem Statement

Overview: Develop an IoT-based air quality monitoring network across Kathmandu Valley with ML-based prediction models. Kathmandu consistently faces seasonal particulate pollution.

Background Context (Nepal): Kathmandu's bowl-shaped topography traps seasonal particulate matter (PM2.5/PM10) from vehicles, brick kilns, and open burning. Low-cost IoT sensor networks combined with time-series forecasting provide localized environmental insights.

2. Research Objectives

›Construct low-cost environmental sensor nodes measuring PM2.5, PM10, temperature, and humidity
›Establish MQTT-based data transmission pipeline to time-series cloud database
›Train LSTM and Prophet machine learning models for 24-hour AQI forecasting
›Analyze spatial pollution hotspots in Kathmandu using GIS mapping
›Calibrate low-cost optical sensors against official Department of Environment reference monitors

3. Proposed Methodology

Hardware assembly using ESP32/Raspberry Pi and Plantower PMS7003 optical sensors
Field deployment across 5 diverse locations (industrial, roadside, residential) in Kathmandu
Data ingestion via MQTT into InfluxDB/PostgreSQL time-series store
Machine learning model development in Python (Pandas, TensorFlow, Prophet)
Validation using Root Mean Square Error (RMSE) against Department of Environment public dataset

$ Worked Example / Sample Scenario

Sample Scenario: IoT nodes deployed in Ratnapark and Lalitpur record elevated PM2.5 levels during dry winter evenings. The LSTM model successfully forecasts a high AQI spike 12 hours in advance, providing automated alerts via Grafana dashboard.

4. Thesis Chapter-by-Chapter Outline

Chapter 1: IntroductionTU/KU/NEB standard

Background, problem statement, research questions, objectives, scope, limitations, and significance of the study

Chapter 2: Literature ReviewTU/KU/NEB standard

Theoretical framework, conceptual models, previous empirical studies in Nepal and developing nations, sensor calibration equations and time-series forecasting architectures, and gap analysis

Chapter 3: Research MethodologyTU/KU/NEB standard

Research design, population/sampling framework, data collection instruments, analytical tools, and ethical considerations

Chapter 4: Data Analysis & ResultsTU/KU/NEB standard

Empirical findings, statistical testing, model estimations, RMSE prediction metrics and spatial AQI heatmaps, and detailed discussion

Chapter 5: Conclusion & RecommendationsTU/KU/NEB standard

Summary of key findings, theoretical contributions, policy recommendations, and future research directions

5. Recommended Tools & Technologies

To implement the practical, technical, or analytical portions of this thesis topic, the following software tools, libraries, or APIs are recommended:

ESP32 / Raspberry PiPythonInfluxDBGrafanaTensorFlow / PyTorchMQTTQGIS

6. Core References & Academic Sources

[1]Department of Environment (Nepal) — Air Quality Monitoring Station Data & Reports
[2]ICIMOD (International Centre for Integrated Mountain Development) — Atmosphere Research Publications
[3]Google Scholar / IEEE Sensors Journal — Calibration of low-cost PM sensors

7. Frequently Asked Questions (FAQs)

Q: Are low-cost optical sensors accurate enough for a thesis?

Yes, provided you perform calibration against official reference data (like DoEnv station readings) and apply humidity correction equations.

Q: How do you transmit data from field nodes to the server?

Nodes can use Wi-Fi in urban locations, or GSM/GPRS modules (SIM800L) using cellular data in spots without Wi-Fi.

Q: What machine learning models work best for air quality prediction?

LSTM (Long Short-Term Memory) networks and Prophet are widely recognized for time-series forecasting with diurnal cycles.

Q: Where can I get official Kathmandu air quality data for validation?

The Department of Environment (Ministry of Forests and Environment) publishes open air quality monitoring reports and real-time portal feeds.