This post shows researchers and policy analysts how to run an AI-enabled qualitative analysis of wetland conversion using the July 2, 2026 PLOS ONE study on Bure and Womberma Woredas (Amhara, Ethiopia). The PLOS ONE paper reports a 48.8% increase in cultivated area across three wetlands (Kotlan, Foket, Wadera) from 1985 to 2021, with 3, 355 ha converted and a 97.27% Landsat LULC classification accuracy in 2021. The post walks through a 7-step workflow to reproduce thematic findings from Landsat outputs, n=396 household surveys, 75 experts, and 12 KIIs, and shows how Evidano supports synthesis, cross-segment comparisons, and stakeholder-ready visualizations.
Key Takeaways
Evidano is an AI-powered qualitative data analysis platform that ingests transcripts, spreadsheets, and remote-sensing tables to accelerate mixed-methods synthesis.
This post demonstrates a reproducible 7-step workflow to synthesize Landsat change maps with n=396 household surveys, 75 experts, and 12 KIIs to surface institutional drivers of wetland conversion.
- The study reports a 48.8% increase in cultivated area across three wetlands from 1985–2021, equal to 3, 355 hectares converted.
- Remote sensing LULC maps achieved high validation, with overall accuracy 97.27% and Kappa 87.19% for 2021.
- The mixed-methods corpus included 396 households, 75 sector experts, and 12 key-informant interviews, enabling cross-segment thematic and statistical analysis.
- Evidano shortens the time from multisource inputs to policy-ready outputs by automating transcription, hierarchical coding, and cross-segment comparisons.
Findings Snapshot
| Date / Metric | Value | Source | Implication |
|---|---|---|---|
| Publication | July 2, 2026 (accepted June 16, 2026) | PLOS ONE | Recent, peer-reviewed |
| Wetland loss (1985→2021) | 48.8% increase in cultivated area; 3, 355 ha converted | Landsat classification (1985, 1995, 2010, 2021) | Substantial landscape change; policy urgency |
| Sample sizes | 396 households; 75 experts; 12 KIIs | Household & expert surveys; KIIs (Mar–May 2022) | Rich mixed qualitative + quantitative corpus |
| Remote sensing accuracy | Overall accuracy 97.27% (2021); Kappa 87.19% | Landsat LULC validation | High confidence in mapped change |
| Key drivers | Youth land claims, unemployment, government allocation | Survey + interviews + institutional review | Institutional & livelihood causes > subsistence needs |
What the study did (plain English)
This section explains what the study did in plain English: the mixed-methods study combined supervised Landsat classification (1985, 1995, 2010, 2021) with structured household and expert surveys and 12 key-informant interviews.
The study used thematic analysis on KIIs, descriptive statistics on surveys (SPSS), and an ordered probit regression (STATA) to link attitudes to household and institutional attributes. Training samples (50–60 per class) and Google Earth Engine compositing produced high-quality LULC maps; household fieldwork ran March–May 2022.
- Remote sensing: Landsat 5/7/8 images composited via Google Earth Engine, supervised maximum likelihood classification, accuracy assessed by confusion matrix.
- Surveys: n=396 households (17 villages) plus 75 sector experts/department heads, using Likert scales for perceptions and attitudes.
- Qualitative: 12 KIIs transcribed and thematically coded to contextualize policy and local decision-making.
So what for researchers and policy teams: AI qualitative analysis of wetland conversion
Audience: UX researchers & environmental analysts
This subsection identifies the audience: UX researchers and environmental analysts who combine spatial, numeric, and textual data.
Researchers combining remote sensing outputs, large survey spreadsheets, and interview transcripts must align formats, extract themes, and compare subgroups (for example, young landless versus older landholders).
The primary lesson from the study is that institutional drivers (land allocation to unemployed graduates) can dominate individual-level motives, so teams should capture and cross-analyze both text and tabular data to surface that effect.
Primary keyword in action: qualitative analysis of wetland conversion
This subsection explains how to apply the primary keyword 'qualitative analysis of wetland conversion' in practice.
Researchers should use 'qualitative analysis of wetland conversion' to tag workflows and reports so decision-makers can find syntheses that link LULC trajectories to narratives from KIIs and attitudes from surveys.
Search-engine friendly outputs include an evidence table tying dates (1985–2021), hectares changed (3, 355 ha), and human drivers (jobs, redistribution policies).
Do more, faster with Evidano
Problem: Multisource mess (maps, spreadsheets, transcripts)
This subsection states the problem: researchers face a multisource mess when combining maps, spreadsheets, and transcripts.
Researchers spend weeks merging numeric LULC tables with hundreds of Likert items and transcribed interviews, and then re-coding themes for each segment.
Solution: Ingest, code, compare (Evidano)
This subsection summarizes the solution: Evidano ingests multisource inputs, performs transcription and AI-assisted coding, and enables cross-segment comparison.
Users can upload remote-sensing LULC tables, household survey spreadsheets, and transcripts or KII audio to Evidano at Evidano. Evidano auto-transcribes with a custom dictionary and PII redaction and generates thematic, frequency, and cross-segment analyses across documents and rows.
Key outputs available in minutes include a thematic codebook with hierarchical codes and subcodes, cross-segment comparisons (for example, young versus older households; agriculture office versus environmental office), and co-occurrence networks that link 'landless youth' to 'wetland allocation' to 'increased cultivation'.
Visualization & handoff
This subsection explains visualization and handoff options: Evidano provides one-click visual exports and reproducible reports.
Users can export word clouds, co-occurrence networks, hierarchical code maps, and frequency tables for stakeholder memos, and export reproducible reports that combine Landsat change tables with qualitative quotes for policy briefs and grant reports.
Security & compliance
This subsection states Evidano's security posture: data is encrypted and proprietary models are used to protect sensitive material.
Data is encrypted at rest and in transit. Evidano uses proprietary LLMs tuned for qualitative research and does not train third-party models on user data, which is critical when working with sensitive KIIs or participant-level survey data.
This week’s 7-step workflow to reproduce the study (two-week pilot)
This section lists a 7-step workflow to reproduce the study in a two-week pilot.
Step 1: Collect and standardize inputs, export Landsat LULC tables, household survey CSVs (n=396), expert CSV (n=75), and KII audio files.
Step 2: Upload to Evidano, enable transcription with a custom Amharic dictionary and PII redaction.
Step 3: Auto-code and review, run AI-assisted thematic coding, review suggested codebook, and lock hierarchical codes.
Step 4: Run cross-segment analysis, compare attitudes by age, landholding, and office affiliation (agriculture versus environment).
Step 5: Merge remote-sensing metrics, import LULC change tables as a spreadsheet and link rows to villages/kebeles for integrated analysis.
Step 6: Visualize and annotate, generate co-occurrence network and export top quotes per theme for policymaker slides.
Step 7: Deliverables, produce a reproducible report (PDF plus CSV codebook) and a short executive brief linking the 48.8% conversion to institutional drivers.
FAQ: AI qualitative analysis of wetland conversion
Can Evidano combine Landsat tables with interview quotes?
Yes, Evidano can combine Landsat tables with interview quotes for side-by-side analysis.
Upload remote-sensing outputs as spreadsheets and transcripts as text or audio. Evidano links numeric rows to text segments using shared keys such as village and year to enable integrated analysis.
How do you ensure thematic rigor?
Researchers retain control to ensure thematic rigor: AI suggests codes but researchers finalize the codebook and auditing artifacts.
AI suggests codes while leaving final codebook control to researchers; users can import existing codebooks, perform inter-coder checks, and export reproducible coding logs for audit trails.
Is this suitable for policy teams?
Yes, the workflow is suitable for policy teams that need stakeholder-ready summaries combining hectares changed, statistical drivers, and curated quotes.
Policy teams can produce summaries that combine hectares changed, ordered probit outputs, and curated participant quotes to support policy recommendations.
Wrapping up: Next steps
This section summarizes next steps: institutional decisions are central to conversion and AI-enabled qualitative workflows speed synthesis from data to decision.
The PLOS ONE study (PLOS ONE) makes a clear case that institutional decisions, not ignorance of wetland value, are central to conversion.
- Try a 2-week pilot to reproduce key tables and thematic maps from the study's data.
- Start by uploading one survey CSV and two KII transcripts to test transcription, code suggestions, and cross-segment outputs.
Ready to turn multisource wetland evidence into policy-ready insight? Try Evidano for free.