Shohinur Pervez Shohan

Multi-Decadal Land-Cover Mapping of the Chittagong Hill Tracts Using Machine Learning and Spatial Validation

Submitted to ICCIT 2026 (double-blind peer review) — currently under review

Originated as B.Sc. thesis (2024, graded A+), then independently extended in 2026 into a full conference paper without institutional funding or supervision.

Research question

Has forest coverage in the Chittagong Hill Tracts changed over three decades (1993–2023)?

Method

Machine-learning classification of six Landsat epochs, comparing Support Vector Machine (78.04%), Random Forest (77.10%), and CART (72.90%) under spatially-blocked holdout validation — a stricter design than a random split, chosen to avoid inflating accuracy through spatial autocorrelation. Benchmarked against the Hansen Global Forest Change dataset. Full pipeline built with free, open-source tools (Google Earth Engine, Python, QGIS).

Key finding

Combined forest area increased 4.4% (+20,693 ha) between 1993 and 2023 — but Dense Forest specifically declined by 8,235 ha, pointing to a shift in forest composition rather than simple loss or gain.

Validation

Area-adjusted 2023 classification accuracy of 73.17% (95% CI: 64.34–82.00%), plus a forest-definition sensitivity analysis to test how much the result depends on a single NDVI threshold. Full code and data pipeline released publicly for reproducibility.

Energy Measurement of Compressed Deep Learning Models: A Literature Review

Preprint, September 2026 — narrative literature review, not yet peer reviewed

Written while reading toward the Green AI research proposal below: an independent literature review examining the measurement layer beneath model compression's energy-savings claims, drawing on a purposively assembled corpus of 53 works (2019–2026).

• Synthesises evidence that software energy estimators and hardware counters disagree by margins comparable to the energy savings compression claims to deliver.
• Shows FLOPs-based proxies correlate weakly with measured energy once memory bandwidth, batch size, and backend kernel realisation are accounted for.
• Finds that compression rankings established on one hardware platform do not reliably transfer to another.
• Sets out a research agenda around three gaps — measurement-tool validation, the nominal-versus-realised compression gap, and cross-platform rank-order preservation — that motivates the in-progress study below.

Hardware-Validated Energy-Aware Reliability Evaluation of Compressed Neural Networks

Master's research proposal (2027 intake) — Phase 1 independently executable; target venues TMLR / Sustainable Computing: Informatics and Systems

A deployment-aware framework bridging efficient and trustworthy machine learning: measures reliability (calibration, robustness) and hardware-validated energy from the same inference passes, then compares compression methods at matched measured energy rather than matched FLOPs.

• Tests whether software energy estimators (CodeCarbon, pyJoules) stay accurate on compressed models — existing validation studies stop at full-precision workloads, leaving quantisation's altered instruction mix and pruning's irregular memory access untested.
• Reconciles contradictory findings on whether compression improves or harms model calibration and robustness, via a controlled sweep across quantisation, structured pruning, unstructured pruning, and distillation with per-class disaggregation.
• Compares compression configurations within matched measured-energy bands instead of matched FLOPs or compression ratio, testing whether the ranking by accuracy agrees with the ranking by reliability (pre-registered hypotheses, Kendall's tau).
• Phase 1 (year 1) runs entirely on hardware already in hand (RTX 3050 6GB, RAPL/NVML/powermetrics); Phase 2 (year 2) is scoped explicitly around resources the applicant cannot independently access — physical power meters, heterogeneous accelerators, and larger model families.
• Extends the same scepticism toward unvalidated measurement that the applicant's undergraduate thesis applied to spatial validation — and builds directly on the literature review above.