EvidenceForge

Designs and audits first-order meta-analyses of primary studies. Use for effect-size extraction, effect-size harmonization, fixed/random/multilevel models, robust variance estimation, heterogeneity, prediction intervals, meta-regression, publication-bias diagnostics, sensitivity checks, coding sheets, reproducible meta-analysis reports, ecological meta-analysis, ecological meta-analysis plus random forest or path modeling, soil-carbon meta-analysis, stock-versus-flux outcome separation, and trait-mediated moderator design.

Adapts evidence synthesis workflows for environmental, ecological, biomedical, and life-science questions. Use for PECO/PICO frameworks, exposure-outcome reviews, ecological heterogeneity, dose-response evidence, risk-of-bias planning, environmental indicators, NDVI or vegetation-index models, partial least squares regression, PLS VIP audits, ecosystem-service relationships, ESR synergy/trade-off mapping, interpretable machine learning, GWR/XGBoost spatial modeling, threshold-oriented ecological management, optimal interval identification, air pollution crop-yield models, ozone/aerosol food-security co-benefits, SIF-based crop productivity, soil biodiversity, aridity gradients, ecosystem stability, climate-stress moderation, soil fauna meta-analysis, ant-mediated carbon cycling, SOC and CO2 dual-outcome synthesis, organism/tissue/time-scale coding, wetland methane scaling, small-patch geospatial upscaling, cryosphere or permafrost evidence products, near-surface ground ice mapping, geospatial environmental ma

Reviews umbrella reviews and second-order meta-analyses. Use when synthesizing existing systematic reviews/meta-analyses, assessing primary-study overlap, duplicate evidence, review quality, AMSTAR/ROBIS-style concerns, discordant conclusions, temporal second-order meta-regression, ecosystem-service trade-offs, and whether review-level statistical pooling is defensible.

Orchestrates systematic reviews, scoping reviews, evidence maps, meta-analyses, umbrella reviews, and AI-assisted evidence synthesis. Use when designing protocols, eligibility criteria, search strategies, screening workflows, coding manuals, effect-size plans, synthesis reports, or reproducible evidence-review packages.

Designs machine-learning assisted systematic review workflows. Use for active-learning screening, deduplication, study classification, LLM-assisted extraction, risk-of-bias triage, topic modeling, moderator discovery, and audit logs, while preserving human verification and transparent evidence-synthesis decisions.