Sign up with your email to run LandPulse analyses.
🔍 Find Parcels by Owner
Last name first. Add first initial for prefix match.
Required. Use "County, ST" format.
Enter an owner name and region to search.
📷 NAIP Aerial Photo Active
Loading imagery dates...
+
Tap map to place photopoint
Generating PDF Report...
Photopoint #1
📍 Loading GPS...
Overlay:40%
📖 Photopoint Guide
Quick Start
🎯 Find your location — Tap to center map on GPS
📍 Add Photopoint — Tap button, then tap map to place
📷 Take photo — Wait for green GPS (±5m), then capture
🔄 Return visits — Previous photo shows as overlay for alignment
5 Rules for Good Photopoints
Permanent anchor — Include a large tree, rock, or fence post that won't move
Clear sightline — Avoid spots where vegetation will block the view
Reproducible position — Stand somewhere you can find again
Consistent direction — Face the same way each visit
Good light — Morning or afternoon, avoid midday glare
What to Photograph
🏠
Structures
Buildings, fences, roads
🌲
Forest edges
Treeline changes, clearing
🌊
Water features
Streams, wetland edges
🌿
Vegetation plots
Meadows, restoration areas
⚠️
Concerns
Erosion, invasives, damage
Using the Overlay (Return Visits)
Tap a saved photopoint marker on map
Use "🎯 To photopoint: Xm" to walk to the spot
Previous photo appears semi-transparent
Move until the overlay aligns with live view
Match horizon first, then anchor objects
80% aligned is still very useful!
What AI Will See Over Time
2 years
New structures, clearing, obvious changes
5 years
Vegetation trends, woody encroachment/forest health rates
10 years
Ecological trajectories, succession patterns
Key Reminders
📡 Wait for good GPS — Green ✓ means ±5m or better
📅 Same time each year — Reduces seasonal confusion
💾 Export regularly — Back up before changing phones
🛰️ Combine with satellite — Ground photos verify what Sentinel detects
LP
LandPulseForest
Satellite stewardship intelligence for working forests
Selected Area
Draw a polygon to begin
Start by defining your property — draw on the map, upload a boundary, or look it up by owner.
Upload boundary
GeoJSON · Shapefile · KML
Tip: enable the 🔍 Owner Search button on the map to find parcels by owner name.
📂 My Saved Properties
Login to save and manage your properties
0 / 500 acres used
FREE
Save Current Property
🔔 Alert Settings
Saved Properties
Loading properties...
📤 Import / Export Portfolio
Sync with Landscape or LOCATE software
Analysis Period
Season Preset
Baseline Period
Current Period
Vegetation & Land Cover
Water & Fire
Riparian Buffer Analysis
🌾 Invasive Species Detection
Detect invasive species using phenological signatures from Sentinel-2 satellite imagery.
Species recommendations based on your property location.
📍 Loading...
0 species recommended for your area
ℹ️ Select a species
Draw a property boundary to see species recommendations for your area,
or select a species from the dropdown to see detection details.
🎯 Smart Scan — Analyzes only species likely in your area (fastest) 🔬 Scan ALL — Checks every species regardless of location ⚠️ Note: Detection accuracy varies by species density and land cover. Field verification recommended.
💧 Wetland Analysis
Comprehensive wetland analysis: classification, change detection, and habitat quality assessment.
Wetland classification automatically combines spring + summer + growing-season imagery — your choice here only changes which composite is rendered on the headline map.
Ancestral Puebloan site probability · Colorado Plateau
⚠ ARPA Restricted — Site probability data is sensitive under
the Archaeological Resources Protection Act. Do not share map tiles or
hotspot coordinates with unauthorized parties.
Combines site probability × post-1985 conifer encroachment to find
areas that were open during the survey era but are now under canopy.
LIDAR DETAIL SCAN
⚠ Area too large for LiDAR scan (max 500 ac). Draw a smaller polygon.
1m LiDAR micro-topography. Use after running the probability
model — draw a tight polygon (≤500 ac) over a specific high-probability
zone. Detects mounds, check dams, walls, and depressions.
SITE MONITORING
⏳
Computing probability surface…
Water proximity is the slowest step (30–90 sec total)
Dark red = highest probability · Ref: Yaworsky et al. 2020
🪲 Forest Health — Comprehensive Detection
Sentinel-2 multi-temporal analysis for PNW bark beetles & defoliators, Midwest white oak decline
with drought index regression, and Oregon white oak encroachment + MOB.
Select Threat
Bark Beetle Mortality — Year-over-year NDMI/NBR decline detects Douglas-fir beetle,
mountain pine beetle, and fir engraver. Red/grey attack = strong signal (NDMI drops 0.15-0.30).
TreeMap host matching identifies likely beetle species.
📡 Jul-Aug imagery (YoY) • NDMI + NBR change • Host species filter
Early Stress / Green Attack — Pre-visual bark beetle detection using NDRS index
(Huo et al. 2021) with CRE red-edge confirmation. Captures stress before crown symptoms appear.
📡 Jun-Aug imagery (YoY) • NDRS + CRE change • 80-88% accuracy (literature) ⚡ Advisory only — high false positive risk from drought. Flags areas for ground-checking.
White Oak Decline — Multi-factor syndrome: drought + Armillaria root rot + Hypoxylon canker
+ two-lined chestnut borer. 200K+ acres severe in Mark Twain NF alone. Detects progressive
crown thinning over 2-5 years in oak-hickory stands, regressed against GRIDMET drought index (PDSI).
📡 Aug-Sep imagery (5yr) • NDVI + NDMI trend • PDSI drought regression • Stand risk scoring 🌡️ Drought-amplified: PDSI < -2 accelerates decline. Wet/dry whiplash is especially damaging.
Oregon White Oak (Q. garryana) — Two parallel threats to declining ecosystem (<15% of historic extent).
1. Conifer encroachment: Doug-fir overtopping oaks due to fire suppression. Detected via
phenological contrast (deciduous oak vs evergreen conifer in winter imagery).
2. Mediterranean Oak Borer (MOB): Exotic invasive beetle (*Xyleborus monographus*) carrying
*Raffaelea montetyi* fungus. Detected in Multnomah/Marion/Clackamas/Washington counties OR.
📡 Winter (Jan-Mar) + Summer (Jul-Sep) • Phenological amplitude • Oak-pixel NDMI trend 🌿 Conservation value: 200+ vertebrate species depend on oak savanna habitat.
🏔️ Whitebark Pine (ESA Threatened) — Keystone high-elevation species under converging threats.
51% of standing whitebark pines are dead (USFWS 2022). Three-threat detection:
1. White Pine Blister Rust: Non-native *Cronartium ribicola* — progressive crown dieback
detected via 5-year NDVI/NDMI decline in WBP pixels. No eradication possible.
2. Mountain Pine Beetle: Targets large seed-producing trees. NDMI/NBR year-over-year change.
3. Succession: Subalpine fir/spruce overtopping WBP due to fire suppression.
📡 Jul-Aug imagery (5yr trend) • TreeMap FORTYPCD 367 + elevation >1800m • GRIDMET drought 🌱 Resistant survivor detection: Green WBP near mortality = seed collection candidates
for USFS Dorena GRC blister rust resistance screening. 1,500+ parent trees tested to date. ⚠️ ESA Section 7 consultation required for any management activity.
🌲 Lodgepole Pine MPB Survivors — Detecting trees that survived the 2000-2015 mountain pine beetle epidemic.
MPB killed ~60% of mature lodgepole across the Rockies. Surviving trees in high-mortality stands
may carry genetic resistance (thicker phloem, aggressive resin, bark chemistry).
Method: Map grey-attack mortality zones (low NDMI) in lodgepole habitat,
buffer 300m, find green canopy within buffer. Height filter (8-28m) excludes regen and Doug-fir/spruce.
📡 Jul-Sep imagery • TreeMap FORTYPCD 281 • ETH canopy height filter 🌲 GPS points exported for field verification and seed collection.
Coordinate with USFS Regional Geneticist for provenance documentation.
🌳 Legacy Tree Detector — Identifies candidate old-growth trees
in fire-adapted ecosystems. Works nationally — adapts to local forest type.
Method: Multi-tier selection using ETH canopy height (10m):
Path A (Height Dominant): ≥ site mean × 1.15 + crown peak — tallest trees in stand
Path B (Crown Shape): ≥ 20m + flat crown (SD < 3.0m) — old-growth morphology even if not tallest
Either path → candidate. LCMS rejects harvest since 1985, Landsat rejects regrowth.
Species ID — Three tiers:
🌲 Confirmed: Western larch via winter NDVI deciduous signal |
🔬 TreeMap: FIA FORTYPCD species lookup |
🏔️ Topo proxy: DEM aspect + elevation fallback
Output classes:
🌲 Tall Tree Candidate (green — passes selection, needs field verification) |
🏆 Probable Legacy (gold — converging evidence: height + crown shape + LCMS + Landsat)
📡 ETH 10m CHM (2020) • LCMS 1985-present • Landsat 1984-present • SRTM 📍 GPS candidate points exported with height, evidence score, entry path,
and species. Load into OnX, Avenza, or Google Earth for field verification. ⚠️ Screening tool — NOT a definitive old-growth map. Cannot distinguish 150yr from 250yr.
Mark candidates with GPS before any mechanical thinning operation.
🎄 Christmas Tree Farm Health — Multi-year time series analysis for planted conifer farms.
Detects progressive decline, needle retention loss (Swiss needle cast, Rhizosphaera,
Dothistroma), root rot (Phytophthora), and insect damage (balsam woolly adelgid, Diplodia).
Method: Summer NDVI (peak vigor) + Winter NDVI (needle retention) + NDMI (moisture stress)
compared across 5 years. Neighborhood z-score detects spatial anomalies. Harvest blocks discriminated
from disease mortality via contiguous-bare-area analysis.
Regions: PNW (Douglas-fir, noble fir) | SE (Fraser fir) | NE (balsam fir, spruce) | MW (Scotch pine, spruce)
📡 Jun-Aug + Dec-Feb imagery (5yr) • Region-specific disease priors • 10m resolution 📍 GPS scouting waypoints exported for declining areas — load into OnX, Avenza, or Google Earth.
Disease probability scored by region and spectral signal match.
🦋 Eastern Spruce Budworm — Choristoneura fumiferana — Most destructive
forest insect in North America. Current outbreak from Quebec (15M+ ha since 2006) is
crossing into northern Maine (3,000 ac confirmed 2024, 178K at risk 2025).
Method: Year-over-year NDMI decline (Jul-Aug) as primary index
(90% accuracy per Rahimzadeh-Bajgiran et al. 2018). Red-edge IRECI change
catches light defoliation that NDVI misses. Multi-year cumulative tracking
for mortality risk (balsam fir dies after 4-5 consecutive years).
Hosts: Balsam fir (most vulnerable) > White spruce > Red spruce > Black spruce
International: Works in Canada using ESA WorldCover + winter NDVI evergreen proxy
📡 Jul-Aug imagery • NDMI + IRECI change • TreeMap spruce-fir codes 📍 GPS scouting points exported for field verification.
Contact Maine Forest Service or SOPFIM (Quebec) for spray coordination.
Oak Wilt — Detects CCI (Chlorophyll/Carotenoid Index) anomalies in deciduous forest.
Red oaks die within weeks; expanding pockets spread via root grafts (~12m/yr).
📡 Jun-Aug imagery • NLCD deciduous forest mask • 80-84% accuracy
Western Conifer Defoliators — Within-season greenup anomaly detects defoliation first,
then discriminates likely agent using temporal trajectory, elevation, and severity pattern.
🦋 Species discrimination: Budworm (slow 10yr decline, mid-high elev) vs Tussock Moth (2-3yr crash, lower elev) 📡 Apr-May vs Jul-Aug greenup • Red-edge CRE confirmation • Elevation + host filter ⚠️ Tussock moth urgency: Can kill trees in 1-2 years. Check B.t.k. spray window.
Southern Pine Beetle — Detects expanding pockets of pine mortality.
SPB kills pines in characteristic spots that grow outward. Trees fade green → yellow → red → gray.
📡 Jul-Sep imagery • Year-over-year NDVI decline • SE US pine belt ⚠️ Early detection critical — Remove infested trees within weeks. Salvage logging + buffer strips.
🌲 Conifer Encroachment — Detects native conifers expanding into meadows and grasslands
due to fire exclusion. Compares Landsat baseline (~2000) to current using fall NDVI +
summer NDVI cross-check. TreeMap species composition identifies encroaching species
(juniper, Doug-fir, ponderosa, etc.).
Output classes:
🌲 Established (green — forest in both periods) |
🔄 Densification (yellow — sparse → dense) |
🔴 New encroachment (red — meadow converted to forest)
📡 Landsat 5/7/8/9 • 30m • 25-year change detection • TreeMap species ID ⚠️ Treatment: mechanical removal, mastication, or prescribed fire. Prioritize meadow edges.
💧 Water Yield Prioritization — Identifies where conifer removal will recover the most
water for aquifer recharge, spring recovery, and streamflow restoration.
Layers combined:
🌲 40yr encroachment severity (meadow→forest weighted 2×) |
💧 OpenET actual evapotranspiration vs meadow reference |
❄️ Snow sublimation model (canopy interception loss) |
🏔️ TWI + slope + aspect (recharge position) |
🗺️ NHD/NWI stream & wetland proximity |
📉 Wetland decline detection (concurrent drying signal)
Output: Priority heat map (red = highest water recovery per acre) +
protection overlay (wetlands & stream buffers for equipment exclusion) +
recoverable water estimate in gallons/acre/year.
📡 Landsat 40yr + OpenET 2016+ + PRISM + 3DEP + NHD + NWI + MODIS snow 💧 Use case: NRCS EQIP applications, municipal source-water protection, watershed restoration grants.
Options match your drawn area. Generic works anywhere; a pest profile adds its host-species mask, biology-matched index, and damage-season gate.
📊 Forest Data Layers
Analyze canopy height, carbon stocks, and forest disturbance history using satellite-derived datasets.
Select Analysis
Canopy Height Analysis — Measures tree height across the property using ETH Global Canopy Height (2020).
Provides mean/max height, canopy cover %, and height distribution.
📡 10m resolution • 2020 baseline • Height histogram included 🌲 Use for: Fuel structure, stand maturity assessment, habitat classification
Carbon Stock Baseline — Estimates total carbon stored in forest biomass using ESA CCI Biomass.
Reports carbon in metric tons and CO₂ equivalent with uncertainty ranges.
📡 100m resolution • 2007-2022 available • Field-calibrated estimates 🌍 Use for: Land trust baselines, conservation value, grant applications ⚠️ Note: Screening-level estimate, not verification-grade for carbon credits
Carbon Trajectory — Anchors current carbon stock on the latest ESA CCI biomass snapshot, then derives the trend direction (gaining / losing / stable) from the LandTrendr NBR greenness trajectory over your chosen window.
📡 Stock snapshot: ESA CCI biomass (latest year ~2022) • Trend: LandTrendr NBR through current year 🌍 Use for: Forest carbon sequestration / loss narratives and stewardship reports ⚠️ Note: Screening-level. Stock magnitude reflects ~2022 biomass; the trend extends to the current year via NBR, not a second biomass measurement.
Forest Health Timeline (LCMS) — Complete 40-year disturbance history using USFS Landscape Change Monitoring System.
Detects gradual mortality (beetles, disease, drought) and abrupt events (fire, harvest, storms).
📡 30m resolution • 1985-present • Landsat time series 🌲 Use for: Temporal context for forest health issues, fuel phase timelines 📅 Shows: Onset year, years active, expansion rate, still active?
LANDFIRE Fuel Profile — National fuel model classification showing surface fuel types (Scott & Burgan 40 models),
canopy bulk density, canopy base height, and canopy cover.
📡 30m resolution • CONUS coverage • Updated through 2023 🔥 Use for: Baseline fuel type identification, CWPP support, fire behavior context ⚠️ Note: Static product — may miss recent mortality or disturbance
Vegetation NDVI Assessment — Current-season vegetation condition from Sentinel-2 at 10m resolution.
Detects canopy stress, mortality, and 3-year greening/browning trends.
📡 10m resolution • Peak growing season (Jun-Sep) • 3-year trend 🛰️ Use for: Current vegetation health, mortality confirmation, stress mapping 📊 Shows: NDVI stats, stress pixel %, temporal trend, fuel model comparison
Fuel Phase Report (Full Synthesis) — The flagship analysis. Synthesizes 5 satellite data sources
to determine where LANDFIRE's fuel model is outdated and how much it underestimates risk.
📡 5 datasets: LANDFIRE + LCMS + Sentinel-2 NDVI + ETH Height + ESA Carbon ⚡ Includes: LANDFIRE Confidence Score (0-100), adjusted risk score, carbon-at-risk ⏱️ Note: Takes 45-90 seconds due to multi-source synthesis
Currently only 2020 data available (ETH baseline)
Available years: 2007, 2010, 2015-2022 (ESA CCI Biomass)
Set the NBR trend window. Baseline can go back to 2007; trend runs through the current year. Carbon stock magnitude is anchored on the latest ESA CCI biomass (~2022).
USFS LCMS tracks slow loss (beetles, disease) and fast loss (fire, harvest) from 1985-present
Sentinel-2 available from 2017-present. Uses June-September cloud-free composite. Includes 3-year trend.
Full synthesis: LANDFIRE + LCMS + Sentinel-2 NDVI + ETH Height + ESA Carbon. Takes 45-90 seconds.
🪚 Fuel Break / Treatment Verification — before/after canopy change for documenting completed work (grant reports, contractor monitoring). Index is dNBR, over phenology-matched leaf-on windows, so it is valid in hardwoods as well as conifer. Documents canopy opening, not fuel load.
Compares a leaf-on window after this date against the same day-of-year window from an
earlier year, so green-up is not mistaken for harvest. The SAR pass sits tight around the event
itself and works through cloud. Import the unit boundary (shapefile) or draw it first.
🌿 Forage & Habitat Analysis
Analyze rangeland forage quality and elk habitat using USDA Rangeland Analysis Platform data.
⚠️ Western US Only: RAP data covers AZ, CA, CO, ID, KS, MT, NE, NV, NM, ND, OK, OR, SD, TX, UT, WA, WY
Maps LandPulse signals onto wildlife habitat fundamentals for the drawn parcel, then compares
them to a cited, evidence-graded knowledge base. Decision support for a professional —
not an autonomous prescription. Unknown variables are flagged for field verification,
never assumed.
Auto-detects your parcel's region and surfaces the curated species that apply there - game and non-game - scored against an evidence-graded, cited knowledge base (100+ recommendations across 7 regions and 28 species). Draw a parcel, run the diagnosis, then check species of interest to refine.
How to read this: the Habitat Report Card shows each fundamental with a
detectability badge — observed,
inferred, or
unknown → field verification needed.
Recommendations are ranked by effect size × evidence grade and split into stand treatments
vs landscape limiting factors.
💧 Aquatic — eDNA & Stream Temperature
Resolves your parcel's HUC12 subwatershed(s) and surfaces documented fish/aquatic eDNA
detections joined to NorWeST modeled August stream temperature, with ESA/T&E status.
Decision support for a professional — not confirmed absence. A reach with no
detection was either not sampled or eDNA was not found; it is never assumed empty.
Pilot coverage: Klamath-Trinity (HUC4 1801). Draw a parcel there and run the
diagnosis to see per-subwatershed species presence, thermal class (cold/cool/warm), riparian
shade where computed, and a restoration signal. Parcels outside the pilot resolve their HUC12s
but return no data yet, with a clear notice.
How to read this: each subwatershed (HUC12) card shows its
species present (eDNA),
thermal class from NorWeST August-mean temperature, mean riparian shade, and a
restoration signal. ESA-listed species are
flagged. Presence is joined to reaches by NHDPlus V2 COMID; verify listed-species
occurrences with the appropriate agency before acting.
Ground Photo Monitoring
Document ground conditions anywhere. Photos are GPS-tagged and show overlay for repeat visits.
No photopoints yet. Tap 🎯 to go to your location, then add a photopoint.
🤖 AI Photo Analysis
Take a photo in the field. Claude compares what it sees against LandPulse's satellite predictions for your exact GPS location.
📡 Powered by Claude vision + LP satellite context. Best for species verification, log quality, and crown health. Not a substitute for a forester.
1. Photo
Next photo type:
Captured photos (0):
💡 Tip: capture wide stand + trunk close-up + canopy overhead at the same spot for the best multi-angle analysis.
3. GPS Location
⏳ Analyzing photo against satellite predictions...
(Typically 20-60 seconds)
📑 Plan Builder — Joint Management Plan
Conversational goals interview with Claude, then auto-generate a CAP-106 / ATFS / FSP-compliant forest stewardship plan PDF for the property.
📡 How it works: Draw a polygon → start a 10-14 turn chat with Claude → answer goals questions → click Generate Plan PDF. ~$0.30/session + ~3 min PDF render.
⚠️ Draw a polygon on the map first.
✅ Goals captured. Ready to generate the plan PDF.
Renders the 33-page Joint Management Plan with these goals + satellite analysis for this property. ~3-5 minutes.
🛡️ FSC Certification Monitoring
Per-FMU monitoring report keyed to FSC-STD-USA-02-2025 (V2.0) indicators, run on the same LandPulse engines
as the Forest tabs: conversion screen (6.9-6.11), near-real-time S1+S2 change (10.9, Annex J), 40-year disturbance history,
harvest openings + regeneration (10.1, 6.6.5), riparian/wetland (6.7), change inside your HCV / RSA / old-growth polygons (9.4, 6.5, 6.8.2),
and the new V2.0 climate-change obligations (6.1.1(3), 7.2.4, 8.1.2) via 30-40 year observed trends on the FMU.
What this is not: a conformance determination. Every indicator carries a tier
(screen / indicative / context) and a field-verify flag, and criteria satellite cannot assess
(chemical use, volumes, RTE presence) are stated as such.
⚠️ Draw or load the FMU boundary on the map first.
Paste GeoJSON (FeatureCollection; properties name, hcv_type) from the management plan's HCV map, or add the current drawn polygon as an HCV.
0 HCV polygons
Harvest units — green-tree retention (6.6.5, 6.6.3)
Paste the harvest-unit GeoJSON (properties name, optional retention_target 0-1, forest_type) or add the current drawn polygon. Each unit is screened for % canopy retained on fresh Sentinel-2 + NAIP (the Silva retention engine).
0 units
⏳ Running indicators…
Typically 1–4 minutes; each check runs in parallel.
Original multi-standard compliance packet (PDF only). Kept for SFI/SBP; FSC users should use the report above.
⚠️ Draw a polygon on the map first.
Standard
⏳ Building compliance packet...
(Typically 60-180 seconds with indicators on)
🏔️ Conservation Context Card
Auto-generated ecological profile from satellite data and reference layers.
🌲 Stand Inventory — TreeMap Intelligence
👤 Plain-English view — technical metrics (BA, BF/ac) hidden. Click any 🤖 indicator for vision-check detail.
USFS TreeMap 30m species composition and size class mapping.
Satellite-derived — field verification recommended before management decisions.
📡 Data: USFS TreeMap — FIA-imputed, 30m CONUS. Species, size class, basal area, carbon.
Static snapshot; the exact vintage is reported with each result. Recent harvests, planting, or mortality may not be reflected.
Analysis
Size Class Map — Colors the property by FIA stand size class (stocking-based). Fastest analysis —
shows where sawtimber, poletimber, and saplings sit on the landscape. No stand delineation overhead.
⏱️ 10–20 sec • Shows tile overlay on map
Property Summary — Full property overview: forest-type composition (FORTYPCD),
QMD, stand height, canopy cover, carbon stocks, and LandTrendr disturbance recovery.
For per-species composition, use Stands v2.
⏱️ 30–60 sec • Includes LandTrendr recovery model
Stands v2 (beta) — Stand boundaries drawn from AEF embedding similarity (not TreeMap label noise). In Region 9 (CT, DE, IA, IL, IN, MA, MD, ME, MI, MN, MO, NH, NJ, NY, OH, PA, RI, VT, WI, WV), species and basal area come from Harvard Forest's 10m FCM10R9 dataset. Outside Region 9, falls back to TreeMap forest-type groups.
⏱️ 30–60 sec • Works in 20 NE/MW states • Requires LANDPULSE_STANDS_EXPERIMENTAL=1 on the server 🧪 Beta — validate against cruise plots before management decisions.
LandTrendr Disturbance History — Pixel-level temporal segmentation of 40 years of Landsat imagery.
Maps when and how severely each pixel was disturbed and current recovery trajectory.
⏱️ 30–60 sec • NBR-based spectral segmentation (Kennedy et al. 2018) 🔥 Use for: Harvest history, fire mapping, beetle impact, recovery monitoring
SIZE CLASS LEGEND
Sapling Poletimber Sawtimber
Based on FIA stocking (STDSZCD), not mean diameter
🪵 Disturbance & Harvest
One answer, with years. Every disturbance in the 40-year Landsat record
— not just the biggest — each with a confidence tier, plus a current-year check that
fills the gap the annual record cannot see. All NBR / radar / embedding based, so it
works in hardwoods instead of only in conifers.
Same day-of-year both sides, so leaf-off and freeze cancel.
Auto finds the undisturbed bulk over a 1 km window, so your polygon can
straddle cut and uncut ground without throwing the correction off.
Optical before/after uses phenology-matched leaf-on windows at the same day-of-year,
so it stays valid in deciduous hardwoods. A Sentinel-1 radar before/after runs
alongside it — that one works under post-storm cloud.
◆ Export gap polygons
Vectorizes the orange-to-red core of the SAR layer — the pixels that moved hard
enough to be believable one at a time. Small cores come out. These are
core footprints, deliberately tighter than the true opening.
📍 Check field points against the detected gaps
Load the waypoints you dropped in the field (onX / Garmin GPX, KML, GeoJSON, or a
lat,lon CSV) and test each one against the change layers. Tells you which openings
the satellite also found, which it missed, and how far off the near misses are —
the misses are the honest calibration.
🔬 Deep scan (opt-in, heavy)
AlphaEarth 64-D embedding sweep at 10 m — finds small group openings the 30 m
Landsat record misses. Slow and compute-heavy, so it does not run by default.
🌿 Silva — Silvicultural Intelligence
The prevention layer. Silva answers three questions about every property:
what IS the forest (Stands V2), what SHOULD it be (Site Classification),
and is it getting there (Site Match + Regeneration Monitoring).
The most effective forest-health strategy is putting the right species on the right sites.
📸 Silva field photo set
1-6 PHOTOS · OPTIONAL · POWERFUL
Each photo informs a different Silva bucket. More photos = stronger evidence. One photo also works — just attach what you have.
0 photos attached~$0.00 est
📸 Photo context active — Site Classification, Site Match, and Recommendations will use it.
📋 Live components
🌲 Current Composition (Stands V2)
LIVE
What IS the forest. AEF-segmented stands with TreeMap species + size class + BA + QMD.
Full stand-level detail and vision validation in the Stands tab.
🕰 Disturbance & Trajectory
LIVE
What WAS the forest. 40-year LandTrendr reading: last disturbance year + severity,
stand maturity class, recovery status (on-track / stalled / complete). Sets the
silvicultural window for prescriptions.
🗺 Ecological Site Classification
LIVE
Synthesizes SSURGO-proxy soils, SRTM topo, PRISM 10-year climate normals,
and LANDFIRE BpS into a property-level site description and rule-based
species recommendation.
⚖ Site Match Assessment
LIVE
Compares current TreeMap composition vs site-recommended species. Flags
mismatches with management implications (encroachment, regen failure,
pest susceptibility).
🌲 Green Tree Retention
POST-HARVEST · FSC
% canopy retention left in a harvest unit, computed on fresh Sentinel-2 + NAIP
(the lagged basemap doesn't matter). A remote-sensing estimate / screening for
monitoring & audit support — a canopy-cover surrogate for basal area, not a measured cruise.
Harvest unit: uses your active boundary — import the land manager's
shapefile/KML (the audit unit of record) or draw the unit.
Load a fresh backdrop below so recent cuts are visible while you draw:
📚 Silva Recommendations
PARTIAL
Citation-backed silvicultural findings mined from USFS Treesearch (60,000+
pubs). 22 findings live; expanding to 100-150 across six batches.
🌳 Special Trees — species toolkits
PROVISIONAL
Pick a species for its tailored tools — occurrence mapping, planting suitability, decline/health, and photo-based bark & form grading. Map tools are gated to the species' native range; photo grading works anywhere.
📸 Bark & bole-form grade (advisory, not a cruise)
Upload 1–4 close-range, geotagged photos of ONE tree's bole/bark. The grade is pinned to the GPS below.
🔬 In development
Silva v0.1 · prevention layer alongside detection algorithms · grant work for US Endowment for Forestry & Communities
🍂 Aspen Detection & Trend Analysis
Map aspen using phenological amplitude — the seasonal NDVI swing
between peak green and leaf-off. Aspen shows massive swing; conifers are flat.
Sentinel-2 at 10m — maps aspen probability from seasonal NDVI amplitude