WIT Summer Mentorship Programme 2025

The Centre for Water Informatics and Technology (WIT) invites undergraduate students to apply for its Summer Mentorship Program (SMP) 2025. This one-month program offers students the chance to work on innovative projects that contribute to WIT's research agenda. Participants will gain hands-on experience, mentorship from WIT faculty and staff, and a stipend upon successful completion. The program this year will run from July 01, 2025, to July 31, 2025. Apply by June 10, 2025, to join us in advancing water informatics and technology.

Duration: The WIT SMP 2025 will take place from July 01, 2025 to July 31, 2025. Applications will be accepted till June 10, 2025.

Eligibility: Undergraduate students from all universities are eligible to apply. Depending on the nature of the work, students of only some specific disciplines may be asked to apply for a particular project. Details for each individual project are published prior to the call for applications. Note that while students from outside Lahore are also eligible to apply, they must arrange their own accommodation for the project duration. 

Selection Procedure: Students apply for specific projects in the shared project list. Student applications will be reviewed by the WIT faculty, and successful applications will be notified accordingly. Each project is assigned to a mentor from the WIT staff who will supervise the student during the program. 

Compensation: Each student will receive a stipend of PKR 20,000, which will be awarded after successfully completing the program.

Project Presentation and Report: At the end of the program, the student will present their work in a joint session and submit a written report. These will be evaluated by the WIT faculty to rank the projects for the best project award.

Best Project Award: The winner of the best project award will receive support to continue the project for an additional period of one month. In addition to the stipend for the extended duration, the student-mentor pair will also have access to a small grant of PKR 50,000 that can be utilized for travel, training, and purchase of materials and equipment related to the project activities.

How to apply: Interested candidates must send their applications by email titled "WIT SMP 2025 Application" to hrwit@lums.edu.pk. The email must include the applicant's CV, academic transcripts, and a cover letter (no more than 300 words) detailing why the applicant is best suited for the proposed work. In the email, the applicant must clearly specify the project for which the application is being submitted. A maximum of two projects can be applied for (with preferences 1 and 2 clearly mentioned).

Below are details for the available projects in summer 2025.

Projects for WIT SMP 2025

Available projects: A total of 8 projects are being offered. The list of projects for the year 2025 can be found below 

Prototyping Off -Grid Communication with AREDN for Resilience and Disaster Scenarios.

Mentor: Ali Akbar, Business Development Manager, WIT.                      
Majors: Computer Science, Electrical Engineering, Network Engineering, Telecommunication.                      
Necessary Skills:: Basic knowledge of networking concepts, interest in wireless communication, hands-on skills in setting up hardware/software systems, ability to conduct independent technical research.                      
Description: This project aims to prototype and test an off -grid communication network using the AREDN (Amateur Radio Emergency Data Network) platform. AREDN is an open-source mesh networking technology that enables broadband communication in areas without existing infrastructure—making it highly relevant for disaster response and remote connectivity. The intern will be responsible for researching, procuring, and setting up the required equipment (e.g., routers, antennas, power sources), configuring mesh nodes, and exploring use cases for how AREDN can support off -grid communication needs in WIT’s focus areas, including early warning systems, field data collection, and community engagement during emergencies. By the end of the mentorship, the project will produce a working AREDN prototype, documented deployment steps, and a set of recommendations on how this technology can be integrated into WIT's ongoing research and capacity-building initiatives.

ESP-NOW Based Soil Moisture Sensor Network

Mentor: Farhan Ammar Ahmad, Team Lead, WIT.                
Majors: Electrical Engineering/Computer Science/Computer Engineering.               
Necessary Skills: Basic understanding of Arduino, ESP32, Electronics Hardware.                
Description: This project develops a low-power soil moisture sensor network using ESP-NOW, where multiple ESP32 slave nodes send data to a central ESP32-GSM gateway. The gateway publishes each node’s data to ThingsBoard via MQTT using unique device tokens. The system focuses on efficient power usage, extended ESP-NOW range, and reliable multi-device cloud integration.

ESP-NOW Based Automated Flood Irrigation Control System

Mentor: Farhan Ammar Ahmad, Team Lead, WIT.                
Majors: Electrical Engineering/Computer Science/Computer Engineering.               
Necessary Skills: Basic understanding of Arduino, ESP32, Electronics Hardware, Motor Control.               
Description: This project aims to develop an ESP-NOW based wireless system for monitoring and controlling flood irrigation in agriculture. Multiple ESP32 slave nodes will be deployed in the field to monitor water level and flow rate, transmitting real-time data to a central ESP32 master node equipped with a GSM module. The master node will publish the data to ThingsBoard or send it directly to the user's mobile phone via SMS. The user can remotely issue control commands—via ThingsBoard or SMS—to the master, which will then instruct the appropriate slave node to open or close irrigation valves, allowing remote control of water flow for efficient field irrigation.

Machine Learning for Earth Sciences: Phase II

Mentor: Hamza Rafique, PhD Candidate, WIT.                
Majors: Computer Science/Electrical Engineering and related disciplines.               
Necessary Skills: Intermediate to advanced programming skills (Python – ML/AI) and fundamentals of GIS.               
Description: After successfully completing the first phase, culminating in the award of best project and a research publication (doi:10.1109/HITE63532.2024.10777226), this fast-paced project will give the selected student hands-on experience with our IoT field data and satellite-based observations to design machine learning models to meet the emerging needs of our agriculture sector. While the first phase focused on time series data from in-situ IoT sensors, this next stage will expand the scope by integrating remote sensing spatial datasets to translate these technological capabilities into scalable solutions for the AgriTech market. The project revolves around the modeling and estimation of soil moisture content, which is essential for the management of agricultural water resources and is a key indicator of various meteorological hazards such as flood risks and drought conditions. In the same context, the Center for Water Informatics and Technology (WIT) has indigenously developed an IoT-based soil moisture monitoring network, which is one of the largest networks in the Indus Basin. Presently, this cost-effective network provides valuable information on the soil moisture, which is being used by farmers and industrial partners in real time, aiding in on-farm decision-making for irrigation scheduling. However, given the vast scale of the agriculture sector in Pakistan and the large proportion of the workforce directly associated with it, there is a critical need to scale this technology for widespread adoption across millions of users. This project aspires to make this transformative leap, moving beyond isolated sensor deployments to a scalable solution by harnessing recent advancements in AI and remote sensing technologies. Specifically, it aims to integrate the coarse-resolution satellite-based soil moisture datasets along with meteorological drivers of soil moisture from global climate models to downscale and generate high-resolution soil moisture estimates at the farm level. The work will begin with learning how to access and manipulate geospatial datasets, including satellite-based soil moisture products (such as SMAP and SMOS) and weather-related data (like rainfall, temperature, and radiation) from global climate models. These datasets will be used to prepare inputs for machine learning models. The student will implement a range of models, starting from basic regression approaches to more advanced architectures like LSTMs and Encoder-Decoder architectures, with the goal of spatial downscaling. Training and validation would be done using farm-scale soil moisture sensors from regional (e.g WIT Network) and global (e.g., COSMOS-UK, ISMN) networks. Lastly, data fusion using multi-sensor data at different resolutions (NDVI, LST), using advanced algorithms, would also be targeted as an additional input to these AI models to test performance improvements. While this project centers on soil moisture, it offers an equal opportunity for students passionate about climate science, geospatial analytics, and artificial intelligence to gain hands-on experience in applying data-driven approaches to pressing environmental challenges. The skills acquired—ranging from handling multi-source remote sensing datasets and designing machine learning workflows to downscaling climate model outputs—are highly transferable to domains such as drought monitoring, flood forecasting, precision agriculture, and sustainable water management. This makes the project not just a specialized technical engagement but a strong stepping stone towards impactful work in AI-driven environmental applications.

UAV-Based Soil Moisture Estimation for Precision Agriculture

Mentor: Ibrahim Rana, Research Assistant, WIT & Muhammad Ahson, Research Assistant, WIT.                
Majors: Electrical Engineering, Computer Science, Environmental Engineering, Geoinformatics, and related disciplines.                
Necessary Skills: Basic programming (Python/Matlab), fundamentals of image processing, interest in UAVs, remote sensing, and IoT systems.                
Description: The Center for Water Informatics and Technology (WIT) at LUMS is actively involved in pioneering research and field-scale deployments in the domains of water management, precision agriculture, and environmental monitoring. Under the umbrella of the National Centre of Robotics and Automation (NCRA), the Agricultural Robotics Lab (NARL), WIT has developed a comprehensive suite of tools, including a fleet of UAVs, multispectral and thermal imaging systems, and an extensive IoT-based soil moisture monitoring network. These resources enable high-resolution data acquisition and analysis, facilitating precision agriculture and informed decision-making. This project will center on the estimation and modeling of soil moisture using remote sensing data acquired from UAV-based platforms. Students will be introduced to the domain of drone operations in precision agriculture: planning and executing aerial surveys, processing imagery into actionable maps, generating crop health estimates based on spatial data, and finally, modeling soil moisture variability across an agricultural field, housed within LUMS. A key component of this project is the integration and validation of remote sensing outputs with ground-truth data from in situ sensors installed within the field. The selected student will explore how sensor networks and aerial platforms can be connected in a feedback-driven system to enhance reliability and calibration of field-scale estimates. Thus, this focused validation work will also offer students a technically grounded experience in field sensor analytics. Finally, this opportunity is particularly suited for students seeking to engage with practical applications of emerging technologies in the context of sustainable agriculture. Participants will develop practical skills in data acquisition, processing, and integration across aerial and ground-based platforms—skills increasingly sought after in both academic research and the rapidly expanding Agritech sector.

Exploring the potential of using Remote Sensing to extract snow data

Mentor: Haseeb Ahmed, Research Associate, WIT.                
Majors: All science and engineering majors.                
Necessary Skills: Data processing (Excel/Python/Matlab).                
Description: Snow plays a key role in the hydrological cycle and can have significant impacts on the water available in a river for large parts of the year. Since snowfall in Pakistan largely occurs in mountainous regions that are often hard to access and place sensors in, remote sensing products present an interesting alternative. The student will research about what remote sensing products are available for the purpose of obtaining snow cover/snow water equivalent estimates and then extract measurements for a catchment in Swat. The extracted data will be validated with snow depth measurements available in certain locations so that the feasibility of using remote sensing data for future projects related to snow/snow depth can be assessed.

Interfacing sensor nodes with a cloud-based controller for Context-aware Sensing and Transmission

Mentor: Nihal Ahmed, Research Associate, WIT.                
Majors: Electrical/Electronics Majors or related.                
Necessary Skills: Familiarity with microcontrollers. Knowledge of the ThingsBoard platform and ESP-IDF is a plus.                
Description: In order to ensure longer operational periods and avoid over and undersampling, sensor nodes dynamically change their sensing frequencies. In the current approach, we use an off-network controller that chooses these frequencies. In this project, the students will interface this controller with a Wireless Sensor Network consisting of a gateway and a few sensor nodes. The controller shall relay its decision to the gateway via the ThingsBoard platform, from where the gateway shall relay the decision to each individual node in the network.

Can games make water conflicts meaningful to students? Comparing games campaigns with farmers and students in Punjab, Pakistan

Mentor: Seemal Nadeem, Research Associate, WIT.                
Majors: All.                
Necessary Skills: Quantitative and Qualitative Data Analysis.                
Description: This project investigates the use of experiential games to understand water conflicts. A game was designed as part of the project and was played in a series of gaming campaigns with farmers living around Namal Lake. The same activity will also be conducted with students at LUMS. With data collection complete, we will move to data analysis. The student will engage with a variety of raw data, including gameplay datasets, responses from pre- and post-game surveys, and qualitative transcripts from the group discussions that followed each session. The role involves conducting both quantitative and qualitative analysis to generate insights on how the game influenced participants’ empathy and shaped their understanding of water-related challenges and behaviors.