diff --git a/frontend/src/hooks/useGearReplayLayers.ts b/frontend/src/hooks/useGearReplayLayers.ts
index a420228..cfd29b9 100644
--- a/frontend/src/hooks/useGearReplayLayers.ts
+++ b/frontend/src/hooks/useGearReplayLayers.ts
@@ -412,7 +412,7 @@ export function useGearReplayLayers(
       }
     }
 
-    // 8. Operational polygons (per model — union of member positions + high-score correlation vessels)
+    // 8. Operational polygons (멤버 위치 + enabledVessels ON인 연관 선박으로 폴리곤 생성)
     for (const [mn, items] of correlationByModel) {
       if (!enabledModels.has(mn)) continue;
       const color = MODEL_COLORS[mn] ?? '#94a3b8';
@@ -420,13 +420,15 @@ export function useGearReplayLayers(
 
       const extraPts: [number, number][] = [];
       for (const c of items as GearCorrelationItem[]) {
-        if (c.score < 0.7) continue;
+        // enabledVessels로 개별 on/off 제어 (토글 대응)
+        if (!enabledVessels.has(c.targetMmsi)) continue;
         const cp = corrPositions.find(p => p.mmsi === c.targetMmsi);
         if (cp) extraPts.push([cp.lon, cp.lat]);
       }
       if (extraPts.length === 0) continue;
 
-      const opPolygon = buildInterpPolygon([...memberPts, ...extraPts]);
+      const basePts = enabledModels.has('identity') ? memberPts : [];
+      const opPolygon = buildInterpPolygon([...basePts, ...extraPts]);
       if (!opPolygon) continue;
 
       layers.push(new PolygonLayer({
diff --git a/frontend/src/services/vesselAnalysis.ts b/frontend/src/services/vesselAnalysis.ts
index 5eea1b7..e18b9c1 100644
--- a/frontend/src/services/vesselAnalysis.ts
+++ b/frontend/src/services/vesselAnalysis.ts
@@ -144,8 +144,9 @@ export interface CorrelationTrackPoint {
 export interface CorrelationVesselTrack {
   mmsi: string;
   name: string;
+  type: string;       // 'VESSEL' | 'GEAR'
   score: number;
-  modelName: string;
+  models: Record<string, number>;  // { modelName: score }
   track: CorrelationTrackPoint[];
 }
 
diff --git a/prediction/main.py b/prediction/main.py
index 30ae293..00c9b33 100644
--- a/prediction/main.py
+++ b/prediction/main.py
@@ -78,8 +78,9 @@ def get_correlation_tracks(
 ):
     """Return correlated vessels with their track history for map rendering.
 
-    Queries gear_correlation_scores (default model) and enriches with
+    Queries gear_correlation_scores (ALL active models) and enriches with
     24h track data from in-memory vessel_store.
+    Each vessel includes which models detected it.
     """
     from cache.vessel_store import vessel_store
 
@@ -87,7 +88,7 @@ def get_correlation_tracks(
         conn = kcgdb.get_conn()
         cur = conn.cursor()
 
-        # Get correlated vessels from default model
+        # Get correlated vessels from ALL active models
         cur.execute("""
             SELECT s.target_mmsi, s.target_type, s.target_name,
                    s.current_score, m.name AS model_name
@@ -95,7 +96,6 @@ def get_correlation_tracks(
             JOIN kcg.correlation_param_models m ON s.model_id = m.id
             WHERE s.group_key = %s
               AND s.current_score >= %s
-              AND m.is_default = TRUE
               AND m.is_active = TRUE
             ORDER BY s.current_score DESC
         """, (group_key, min_score))
@@ -107,31 +107,41 @@ def get_correlation_tracks(
         if not rows:
             return {'groupKey': group_key, 'vessels': []}
 
-        # Collect target MMSIs
-        vessel_info = []
-        mmsis = []
+        # Group by MMSI: collect all models per vessel, keep highest score
+        vessel_map: dict[str, dict] = {}
         for row in rows:
-            vessel_info.append({
-                'mmsi': row[0],
-                'type': row[1],
-                'name': row[2] or '',
-                'score': float(row[3]),
-                'modelName': row[4],
-            })
-            mmsis.append(row[0])
+            mmsi = row[0]
+            model_name = row[4]
+            score = float(row[3])
+            if mmsi not in vessel_map:
+                vessel_map[mmsi] = {
+                    'mmsi': mmsi,
+                    'type': row[1],
+                    'name': row[2] or '',
+                    'score': score,
+                    'models': {model_name: score},
+                }
+            else:
+                entry = vessel_map[mmsi]
+                entry['models'][model_name] = score
+                if score > entry['score']:
+                    entry['score'] = score
+
+        mmsis = list(vessel_map.keys())
 
         # Get tracks from vessel_store
         tracks = vessel_store.get_vessel_tracks(mmsis, hours)
 
         # Build response
         vessels = []
-        for info in vessel_info:
+        for info in vessel_map.values():
             track = tracks.get(info['mmsi'], [])
             vessels.append({
                 'mmsi': info['mmsi'],
                 'name': info['name'],
+                'type': info['type'],
                 'score': info['score'],
-                'modelName': info['modelName'],
+                'models': info['models'],  # {modelName: score, ...}
                 'track': track,
             })