I am a postdoctoral researcher at the University of Arizona, School of Plant Sciences, US, with experience in machine learning for plant phenotyping, disease detection, underground plant root growth monitoring using AI, precision agriculture using drone imagery, drone image processing, signal processing, machine learning, data science and computer vision.  My current research integrates deep learning and UAV-based remote sensing to advance sustainable farming. I hold a Ph.D. in Electrical and Photonics Engineering from the Technical University of Denmark, where I focused on drone image processing for district heating systems. Previously, I worked as a Senior Software Engineer at Samsung R&D Institute in Bangladesh (SRBD). I earned my B.Eng. in Computer Engineering and M.Eng. in Electronics and Computer Engineering from Chonnam National University, South Korea. 

The University of Arizona’s Center for the Integration of Research, Teaching, and Learning (CIRTL) Postdoc Pathway Program is a one-year teaching certification that provides training in effective teaching methods, along with a short co-teaching assignment and guidance from a faculty mentor.

SEMESTER 1: PREPARE & PLAN

• Completed an  open online course - An Introduction to Evidence-Based Undergraduate STEM Teaching

• Participated in an elective CIRTL workshop: "Writing an Effective Teaching Philosophy Statement." 

• Engage in a weekly learning community to discuss teaching strategies, challenges, and best practices.

• Identified the course and faculty mentor for the co-teaching experience: PLS 481/581 (Spring 2025) – Computational Plant Sciences in the School of Plant Sciences with Dr. Alexander Bucksch. This course was offered at both the graduate and undergraduate levels. 

• Collaboratively developed a co-teaching plan

SEMESTER 2: TEACH & REFLECT

• Observed co-teacher and prepared my module on AI and machine learning to teach.

• Taught course (5 weeks, Twice a Week) - Developed and delivered a six-week curriculum for plant science students. The first three weeks focused on foundational AI concepts and hands-on machine learning applications in plant disease detection, coding exercises, group discussions, and peer instruction. The fourth and fifth weeks covered essential programming skills, including Python debugging, command-line usage, quantum computing paper discussion, and in-depth project discussions. Classes were held twice a week in 2-hour sessions. Reflected on teaching practices through journaling and weekly meetings with the co-teacher. 

• Taught course (1 week) - Additionally, two weeks into the course , a student registered late, and I provided private instruction for one week to help them catch up. 

• Engaged in biweekly postdoc pathway learning community to discuss.

My goals for the Postdoc Pathway last year were to: 

• Improve as an instructor by learning and applying inclusive teaching methods—such as active student engagement and varied teaching styles—to support diverse learners in my co-taught courses.

• Develop my own teaching philosophy through practical experience and by collaborating with other educators in the CIRTL Postdoc Pathway Program, deepening my understanding of evidence-based practices.

• Use the program’s resources and network to strengthen my preparation for academic positions that value excellence in both teaching and research.

Before joining the CIRTL Postdoc Pathway Program, I had limited knowledge of active learning and its implementation in the classroom. I believed that effective teaching primarily involved delivering content clearly and concisely. I assumed that if I explained concepts well, students would understand and retain the material. Assessments and activities seemed secondary, serving only to test students' comprehension after lectures. I did not fully appreciate the role of structured learning objectives, student engagement strategies, or the importance of inclusive teaching practices.

Through the program, I quickly realized that effective teaching is much more than content delivery, it requires intentional planning, interactive engagement, and ongoing reflection. One of my biggest misconceptions was that all students learn the same way I do. However, I learned that students have diverse backgrounds, learning styles, and motivations, all of which influence how they engage with the material. I also became more aware of my own unconscious biases and how they can affect student participation and classroom dynamics.

One of the most impactful components of the program was the online course Introduction to Evidence-Based Undergraduate STEM Teaching in Fall 2024. Through this course, I gained a deeper understanding of evidence-based teaching practices, including active learning strategies, learning objectives, and assessment alignment. Each week, our Faculty Learning Community (FLC) sessions provided a space to discuss these concepts further, reflect on our experiences, and explore how to implement them effectively in the classroom. CIRTL helped me shift my perspective. I learned that teaching should begin with well-defined learning objectives that align with assessments and classroom activities, ensuring a structured and effective learning experience.

One of the most rewarding experiences of the program was co-teaching PLS 481/581 Computational Plant Science in Spring 2025 at the University of Arizona. This course, designed for students with little to no prior coding experience, introduced them to computational approaches in plant science. I had the opportunity to teach Module 2, focusing on AI and machine learning applications in plant sciences.

Through the FLC program, I explored key pedagogical frameworks, including Bloom’s Taxonomy, and learned how to effectively align learning objectives with assessments and activities. I applied this framework to my teaching by ensuring students progressed through different levels of cognitive learning. Initially, they engaged in foundational learning, where they remembered and understood key AI and machine learning concepts. Then, through hands-on coding exercises, they applied their knowledge to real-world datasets. Finally, students analyzed model outputs and created their own AI-driven plant disease detection model, demonstrating higher-order thinking skills.

It was exciting to see students develop new skills and gain confidence in implementing AI models, particularly in plant disease detection. The hands-on coding sessions were a highlight, as I observed students progress from limited knowledge to successfully applying AI techniques to real-world problems. Implementing active learning strategies, such as peer discussions and guided coding exercises, made a significant difference in their engagement and comprehension. By structuring lessons around Bloom’s Taxonomy, I ensured that students moved beyond rote memorization to deeper understanding and practical application.

One of the challenges I faced was balancing the needs of students with varying levels of prior knowledge. Some students struggled with coding, while others grasped the concepts more quickly. I had to adapt my teaching strategies to provide additional support to those who needed more help. Additionally, while I enjoyed teaching practical applications of AI, I sometimes found it challenging to ensure that students fully understood the theoretical foundations behind the concepts. This experience emphasized the importance of finding the right balance between theory and practice.

At the end of the module, I collected anonymous student feedback through a Google Form to assess their learning experience. Many students expressed appreciation for the active learning approach, particularly the hands-on exercises and peer discussions. They highlighted how these methods helped them grasp complex AI concepts more effectively. Several students also mentioned that they would like to see more courses applying this interactive and application-driven teaching style in their curriculum, reinforcing the value of evidence-based teaching strategies.

This experience has truly changed my perspective on teaching. It highlighted the importance of not just what I teach but how I teach, ensuring that learning is interactive, engaging, and directly applicable to real-world problems. I now feel even more confident in using evidence-based strategies to encourage deeper student engagement and understanding.

Additionally, CIRTL emphasized the importance of inclusive teaching. Through the program, I also refined my approach to active learning. I learned that incorporating interactive techniques, such as retrieval practice, peer discussions, and project-based learning enhances student engagement and comprehension. Implementing these strategies in my course allowed students to not only absorb information but also actively participate in constructing their own knowledge.

Participating in CIRTL has fundamentally changed my approach to teaching. I now recognize that effective instruction is not just about delivering content but about creating meaningful learning experiences through evidence-based strategies. Moving forward, I plan to continue refining my teaching methods, incorporating more active learning strategies, and further exploring ways to promote inclusivity in the classroom. Most importantly, I have learned that teaching is an ongoing process of reflection and adaptation, one that I am excited to continue developing.

Course: PLS 481/581 Computational Plant Science, School of Plant Sciences, University of Arizona

Instructor: Dr. Alexander Bucksch 

Description: This course is designed for both undergraduate (PLS 481) and graduate (PLS 581) students, introducing them to computational approaches in plant sciences. The goal of the course is to help students become comfortable with programming and basic algorithm development for plant simulation and imaging. Designed for students new to programming or those who do not regularly code, the course introduces computational techniques to explore plant biology. It covers fundamental concepts such as algorithm design, plant growth simulation, and pattern formation using the Diffusion-Limited Aggregation (DLA) algorithm, as well as imaging techniques and basic Python programming. Through hands-on exercises and project-based learning, students develop problem-solving skills to simulate plant growth from the cellular to the organism level and analyze plant morphology using imaging techniques. The course encourage active participation, critical thinking, and collaboration, preparing students for computational research in plant sciences. 

Syllabus of the Course (Click)

Co-Teaching Summary: Dr. Alexander Bucksch and I share a strong interest in combining AI with plant sciences to enhance student learning. Our collaboration integrates advanced computational techniques into agricultural research education, encouraging deeper understanding of both fields.  I designed and introduced Module 2 of the PLS 481/581 Computational Plant Science course, focusing on AI and machine learning applications in plant sciences. Over a total of five weeks, I taught this module in two-hour sessions, twice a week. During the first three weeks, I provided plant science students with foundational knowledge in AI and guided them through hands-on implementation of AI-driven projects. During the remaining two weeks, I taught debugging Python code, led project discussions, and facilitated paper discussions on quantum computing and its applications in biology.   My approach emphasized practical coding exercises, real-world applications, and interactive discussions to help students apply machine learning techniques to plant phenotyping and related areas. 

My contributions included:

• Taught core AI and machine learning principles relevant to plant science and phenotyping.

• Designed and led hands-on coding sessions where students implemented AI models for plant disease detection and analysis.

• Introduced students to machine learning workflows, including data simulation, labeling, model training, and evaluation, with applications in plant biology.

• Facilitated group discussions and collaborative problem-solving to reinforce AI applications in agricultural research.

• Guided students in building, tuning, and evaluating machine learning models using real public datasets, focusing on leaf disease detection.

• Covered foundational Python programming, debugging techniques, command-line usage, and led detailed project discussions to build practical coding and problem-solving skills.

• Provided individualized support, including to students who joined late in the semester, ensuring they could catch up and fully participate.

• Conducted a qualitative survey at the end of the module to gather student feedback on engagement, understanding, and learning outcomes.

Following the completion of my sessions, I observed remaining classes led by my teaching mentor. During this period, students continued developing their AI and machine learning projects, which they later presented to demonstrate their ability to apply AI techniques to real-world plant science problems.

Everything below is clickable. 

CIRTL letter of completion - Introduction to evidence-based undergrad STEM teaching 

Certificate - Fall 2024 Faculty Learning Community

Certificate - Spring 2025 Faculty Learning Community

Certificate - Postdoc Pathway Fellows Program

Certificate - Mentoring Institute Online Training   

Teaching Journal Highlights 

Co-teaching plan for PLS 481/581 

Example slide from the first class of the Machine Learning module 

All Machine Learning codes taught in class from Module 2 are available on my GitHub

Example of Session: Final Project Selection and Evaluation 

Taught Module 2 and Received Feedback from Student

Student Feedback on Overall Class Experience  

Teaching Philosophy

My first teaching experience was during my PhD as a Teaching Assistant (TA) for a Digital Video Technology course. In this role, I supported students by assisting in class activities, helping them solve problems during lab exercise sessions, and providing guidance during office hours. I co-mentored 5 student projects and conducted 8 lab exercise sessions (each lasting 2 hours). While I was not directly responsible for delivering lectures, I applied active learning techniques by engaging students in hands-on problem-solving. Additionally, in Spring 2025, I led a graduate-level pre-seminar discussion in the Department of Plant Sciences Seminar at the University of Arizona, with a group of 5 graduate students, where I facilitated critical discussion on plant phenotyping research using deep learning. This experience reinforced my commitment to encouraging an interactive, student-centered learning environment.

Currently, in Spring 2025, I am co-teaching a Computational Plant Sciences course at the University of Arizona, a 4-credit course that meets twice a week for two-hour sessions. The course explores computational methods, algorithm design, and the application of AI and machine learning in plant sciences. I taught the machine learning and AI components, guiding students in applying these techniques to plant phenotyping and related areas. My class consisted of a diverse group of students, including three PhD students and two undergraduates from different countries, which enriched discussions and perspectives.

My teaching approach emphasized active learning and student collaboration. Each class included group activities, peer instruction, and problem-solving sessions, where students were randomly grouped to tackle challenges and discuss their solutions. I also provided one-on-one mentorship during office hours, which significantly enhanced student engagement and participation. I strongly believed that active learning—where students engaged in activities promoting critical thinking, collaboration, and problem solving—led to a deeper understanding of concepts.

To continuously improve my teaching, I collected student feedback through anonymous Google Forms at the end of my module. This allows students to provide honest insights on what worked well and what could be improved. Students highlighted the value of interactive coding exercises, real-world applications, and active discussions. They appreciated the opportunity to collaborate, present their approaches, and receive feedback during class. One student noted, "The instructor encouraged us to share our in-class assignments, and we had discussions on different approaches, which provided a great active learning experience." Another student emphasized the importance of "practical coding in every class," while another stated, "The application of AI and machine learning to disease diagnostics was especially valuable." Recent feedback also provided suggestions for improvement, such as recording in-class explanations for later review and incorporating additional machine learning examples for model development. I value these insights and actively work to refine my instructional methods accordingly.

I am committed to integrating a variety of evidence-based teaching strategies to create an inclusive and engaging learning environment. I have found that approaches such as real-world case studies, project-based learning, collaborative coding exercises, and traditional lectures can be highly effective when thoughtfully applied. I also recognize the value of flexible delivery formats—such as in-person lectures, online instruction, and hybrid models—to accommodate a wide range of student needs and learning preferences. My goal is to blend these methods to support student success, promote active participation, and foster critical thinking across diverse educational settings.

In conclusion, I view teaching not only as a way to transfer knowledge but as an opportunity to inspire both intrinsic motivation—by nurturing students’ curiosity, creativity, and confidence, and extrinsic motivation, by helping them develop the practical skills and credentials they need to succeed in their careers. I strive to build a classroom environment where students are encouraged to take intellectual risks, collaborate meaningfully, and connect their learning to real-world challenges. By encouraging both personal growth and professional readiness, I hope to empower the next generation of scientists, researchers, and innovators.