BZPEERReading, trust and collaboration for research
Menu

Discover

GraphFollow connections around a paper, topic or saved view.

Workspaces

HomePick up where your research flow left off.InboxHandle requests, replies and notifications from one place.CollectionsCurate reading lists, evidence sets and shareable dossiers.ResearchSee your private provenance graph, trail and imports.CollaborationMove from discovery into focused discussion rooms.PublishDraft, preview and publish full-text research articles.

Network

ExpertsFind specialists worth following or asking for help.CommunitiesJoin research circles organized around shared work.PartnersSee external organizations active around the same topics.

Opportunities

ListingsBrowse roles, calls and collaborations with clearer fit signals.

Account

Log inReturn to your reading and collaboration workspace.Create accountStart saving work, following people and joining teams.
Log inCreate account

Researcher profile

Reza M. Asiyabi

Reza M. Asiyabi contributes to research discovery and scholarly infrastructure.

ResearcherAffiliation not importedOpen to collaborate
Artificial IntelligenceComputer VisionMachine Learningecon.GNq-fin.EC

Trust snapshot

Quick read

Trust 15 - Baseline
3works
0followers
5topics
4close collaborators

Actions

Decide how to stay connected

Follow researcher0

Research graph

See the researcher in context

Open full explorer

Inspect adjacent work, topics, institutions and collaborators without jumping out to a separate graph page.

Building this graph slice

BZPEER is loading the nearby papers, people, topics and institutions for this page.

Published work

3 published item(s)

preprint2026arXiv

Process-Guided Concept Bottleneck Model

Concept Bottleneck Models (CBMs) improve the explainability of black-box Deep Learning (DL) by introducing intermediate semantic concepts. However, standard CBMs often overlook domain-specific relationships and causal mechanisms, and their dependence on complete concept labels limits applicability in scientific domains where supervision is sparse but processes are well defined. To address this, we propose the Process-Guided Concept Bottleneck Model (PG-CBM), an extension of CBMs which constrains learning to follow domain-defined causal mechanisms through biophysically meaningful intermediate concepts. Using above ground biomass density estimation from Earth Observation data as a case study, we show that PG-CBM reduces error and bias compared to multiple benchmarks, whilst leveraging multi-source heterogeneous training data and producing interpretable intermediate outputs. Beyond improved accuracy, PG-CBM enhances transparency, enables detection of spurious learning, and provides scientific insights, representing a step toward more trustworthy AI systems in scientific applications.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

StruMPL: Multi-task Dense Regression under Disjoint Partial Supervision and MNAR Labels

Estimating forest aboveground biomass (AGB) from Earth observation combines two structurally incompatible label sources: spaceborne lidar provides canopy structure at millions of locations but no biomass estimate, and ground-based plots provide biomass at thousands of biased locations but no metrics of structure. No single training sample carries labels for all target variables, plot labels are missing not at random (MNAR), and biomass is linked to the structural variables by known but biome-specific allometric laws. We formalise this as multi-task dense regression under heterogeneous disjoint partial supervision with MNAR labels and inter-task physical constraints, and propose StruMPL to address it jointly. A shared encoder feeds per-variable regression, imputation, and propensity heads for spatial MNAR correction, and a learnable physics module that evaluates the inter-task constraint on the model's own predictions at every pixel. The supervised loss uses an Augmented IPW (AIPW) pseudo-outcome with stop-gradients on the propensity and on the imputation baseline; we show analytically and empirically that both are necessary for joint optimisation to recover IPW-weighted stationary points while keeping the loss bounded. On two ecologically distinct biomes, StruMPL outperforms ablation variants and the closest published method on AGB RMSE and bias, with a stratified analysis showing AIPW reduces high-AGB bias by ~54%.

0 citations0 reviewsNo code linkedOpen access
preprint2026arXiv

Using satellite imagery to map rural marketplaces and monitor their activity at high frequency

In many rural areas of low- and middle-income countries, weekly gatherings of buyers and sellers are the most tangible manifestation of the market economy. Knowing these markets' whereabouts and activity over time could provide insights in otherwise data-scarce environments, helping researchers and policymakers to better understand poor rural economies. But these markets are by nature informal and scattered widely across often-remote regions. As a result, data on this fundamental institution are sparse and inconsistent. We develop, test, and apply a method to fill this gap, leveraging market activity's unique temporal and visual signature in satellite imagery. Using secondary data from Kenya, Malawi, and Mozambique, we first confirm that we detect markets with high sensitivity and specificity. We then derive a map of 1,776 markets in Ethiopia and track their activity at up-to-weekly frequency between 2017 and 2024. Measured market activity exhibits seasonal patterns following local agricultural calendars and responds to weather and conflict shocks. Our approach is applicable wherever satellites can regularly acquire images of rural periodic markets and requires no ground data. Once markets are mapped, our approach can be fully automated to produce an up-to-weekly measure of economic conditions in areas where such data is otherwise generally not available.

0 citations0 reviewsNo code linkedOpen access