foo

metrics_stats.py

@@ -3,13 +3,24 @@
 import json
 import numpy as np
 from pathlib import Path
-from datetime import datetime
+from datetime import datetime, timedelta
+from scipy import sparse
+from scipy.sparse.linalg import spsolve
 from scipy.stats import pearsonr
 import rasterio
 from rasterio.warp import transform as transform_coords
 
 from metrics_indices import BLUE_BAND, GREEN_BAND, RED_BAND
 
+WHITTAKER_LAMBDA_DAYS_SQ = 400.0
+
+
+def _norm_date_key(s):
+    if s is None:
+        return None
+    t = str(s).strip()
+    return t.split("T")[0][:10] if "T" in t else t[:10]
+
 
 def load_timeseries(filepath):
     """Load JSON timeseries and return dict mapping date -> value."""
@@ -22,14 +33,24 @@ def load_timeseries(filepath):
 
 def match_dates(fusion_ts, phenocam_ts):
     """Match dates between timeseries, return aligned numpy arrays (filter None values)."""
-    common_dates = set(fusion_ts.keys()) & set(phenocam_ts.keys())
+
+    def _bundle(m):
+        out = {}
+        for k, v in m.items():
+            nk = _norm_date_key(k)
+            if nk and nk not in out:
+                out[nk] = v
+        return out
+
+    fa, pa = _bundle(fusion_ts), _bundle(phenocam_ts)
+    common_dates = set(fa) & set(pa)
     fusion_vals = []
     phenocam_vals = []
     dates = []
 
     for date in sorted(common_dates):
-        fusion_val = fusion_ts[date]
+        fusion_val = fa[date]
-        phenocam_val = phenocam_ts[date]
+        phenocam_val = pa[date]
         if fusion_val is not None and phenocam_val is not None:
             fusion_vals.append(fusion_val)
             phenocam_vals.append(phenocam_val)
@@ -94,19 +115,21 @@ def nse(y_true, y_pred):
 
 
 def calculate_temporal_metrics(fusion_ts, phenocam_ts):
-    """Calculate all 6 temporal metrics."""
+    """Temporal metrics vs PhenoCam (nse_pc; nse is the same value)."""
     fusion_vals, phenocam_vals, dates = match_dates(fusion_ts, phenocam_ts)
 
     if len(fusion_vals) < 2:
         return None
 
+    n_pc = nse(phenocam_vals, fusion_vals)
     metrics = {
         "pearson_r": pearson_correlation(phenocam_vals, fusion_vals),
         "r_squared": r_squared(phenocam_vals, fusion_vals),
         "rmse": rmse(phenocam_vals, fusion_vals),
         "mae": mae(phenocam_vals, fusion_vals),
         "nrmse": nrmse(phenocam_vals, fusion_vals),
-        "nse": nse(phenocam_vals, fusion_vals),
+        "nse_pc": n_pc,
+        "nse": n_pc,
         "n_samples": len(fusion_vals),
         "date_range": {"start": dates[0], "end": dates[-1]} if dates else None,
     }
@@ -129,6 +152,59 @@ def calculate_phenocam_stats(phenocam_ts):
     }
 
 
+def _s2_kept_date_set(base: Path, strategy: str) -> set:
+    path = base / "raw" / "preselection" / "s2_preselection.json"
+    if not path.exists():
+        return set()
+    with open(path) as f:
+        rows = json.load(f)
+    key = f"excluded_{strategy}"
+    out = set()
+    for e in rows:
+        if e.get(key):
+            continue
+        nk = _norm_date_key(e.get("date"))
+        if nk:
+            out.add(nk)
+    return out
+
+
+def _whittaker_smooth_dict(obs_dates, obs_values, lam: float, n_min: int = 3):
+    """Daily Whittaker (weights 1 at obs); returns {YYYY-MM-DD: z}."""
+    pairs = [
+        (_norm_date_key(d), float(v))
+        for d, v in zip(obs_dates, obs_values)
+        if v is not None and _norm_date_key(d)
+    ]
+    if len(pairs) < 2:
+        return {}
+    days = sorted({p[0] for p in pairs})
+    t0 = datetime.strptime(days[0], "%Y-%m-%d").date()
+    t1 = datetime.strptime(days[-1], "%Y-%m-%d").date()
+    n = (t1 - t0).days + 1
+    if n < n_min:
+        return {}
+
+    w = np.zeros(n)
+    y = np.zeros(n)
+    for dk, val in pairs:
+        i = (datetime.strptime(dk, "%Y-%m-%d").date() - t0).days
+        if 0 <= i < n:
+            w[i] = 1.0
+            y[i] = val
+
+    D = sparse.diags(
+        [1.0, -2.0, 1.0], [0, 1, 2], shape=(n - 2, n), format="csc", dtype=np.float64
+    )
+    H = D.T @ D
+    Wm = sparse.diags(w.astype(np.float64), format="csc")
+    z = spsolve(Wm + lam * H, w * y)
+    out = {}
+    for i in range(n):
+        out[(t0 + timedelta(days=i)).isoformat()] = float(z[i])
+    return out
+
+
 def _get_spatial_stats_from_raster(raster_file, site_position):
     """Extract spatial statistics (mean, std, min, max) from GCC raster in 3x3 window."""
     try:
@@ -316,15 +392,52 @@ def calculate_all_metrics(season, site_name, site_position):
     if phenocam_stats:
         results["phenocam_stats"] = phenocam_stats
 
-    # Calculate S2 baseline metrics once (S2 data is identical across scenarios)
+    baseline = {}
-    s2_ts_path = (
+    s2_ts = {}
-        base / "processed_aggressive_sigma20" / "gcc" / "s2" / "timeseries.json"
+    for sub in ("processed_aggressive_sigma20", "processed_nonaggressive_sigma20"):
-    )
+        p = base / sub / "gcc" / "s2" / "timeseries.json"
-    s2_ts = load_timeseries(s2_ts_path)
+        if p.exists():
+            s2_ts = load_timeseries(p)
+            if s2_ts:
+                break
     if s2_ts:
-        s2_metrics = calculate_temporal_metrics(s2_ts, phenocam_ts)
+        m0 = calculate_temporal_metrics(s2_ts, phenocam_ts)
-        if s2_metrics:
+        if m0:
-            results["baseline"] = {"s2": s2_metrics}
+            baseline["s2"] = m0
+        for strategy in ("aggressive", "nonaggressive"):
+            kept = _s2_kept_date_set(base, strategy)
+            filtered = [
+                (k, v)
+                for k, v in sorted(
+                    s2_ts.items(), key=lambda x: _norm_date_key(x[0]) or ""
+                )
+                if _norm_date_key(k) in kept and v is not None
+            ]
+            if not filtered:
+                continue
+            sub_ts = dict(filtered)
+            mcf = calculate_temporal_metrics(sub_ts, phenocam_ts)
+            if mcf:
+                baseline.setdefault("s2_cloudfree", {})[strategy] = mcf
+            obs_d, obs_v = zip(*filtered)
+            smooth = _whittaker_smooth_dict(obs_d, obs_v, WHITTAKER_LAMBDA_DAYS_SQ)
+            if smooth:
+                mw = calculate_temporal_metrics(smooth, phenocam_ts)
+                if mw:
+                    baseline.setdefault("s2_whittaker_lambda400", {})[strategy] = mw
+
+    for strategy in ("aggressive", "nonaggressive"):
+        p = base / f"processed_{strategy}_sigma20" / "gcc" / "s3" / "timeseries.json"
+        if not p.exists():
+            continue
+        s3_ts = load_timeseries(p)
+        if s3_ts:
+            m3 = calculate_temporal_metrics(s3_ts, phenocam_ts)
+            if m3:
+                baseline.setdefault("s3", {})[strategy] = m3
+
+    if baseline:
+        results["baseline"] = baseline
 
     # Calculate fusion metrics for each scenario
     for strategy in ["aggressive", "nonaggressive"]:
@@ -378,15 +491,17 @@ def calculate_all_metrics(season, site_name, site_position):
             if spatial_metrics:
                 results["spatial"][scenario_name] = spatial_metrics
 
-    # Add summary
+    # Add summary (primary: NSE vs PhenoCam; R² kept for comparison)
     if results["temporal"]:
-        best_temporal = max(
+        ti = list(results["temporal"].items())
-            results["temporal"].items(),
+
-            key=lambda x: x[1].get("r_squared", -1)
+        def _score(k):
-            if x[1].get("r_squared") is not None
+            return lambda x: x[1].get(k) if x[1].get(k) is not None else float("-inf")
-            else -1,
+
-        )
+        results["summary"] = {
-        results["summary"] = {"best_temporal_scenario": best_temporal[0]}
+            "best_temporal_scenario": max(ti, key=_score("nse_pc"))[0],
+            "best_temporal_scenario_by_r2": max(ti, key=_score("r_squared"))[0],
+        }
 
     if results["spatial"]:
         best_spatial = max(

webapp/index.html

@@ -561,8 +561,8 @@
             
             const scenarios = ["aggressive_sigma20", "aggressive_sigma30", "nonaggressive_sigma20", "nonaggressive_sigma30"];
             const scenarioNames = ["Aggressive σ20", "Aggressive σ30", "Non-aggressive σ20", "Non-aggressive σ30"];
-            const metrics = ["pearson_r", "r_squared", "rmse", "mae", "nrmse", "nse"];
+            const metrics = ["pearson_r", "r_squared", "rmse", "mae", "nrmse", "nse_pc"];
-            const metricLabels = { pearson_r: "r", r_squared: "R²", rmse: "RMSE", mae: "MAE", nrmse: "nRMSE", nse: "NSE" };
+            const metricLabels = { pearson_r: "r", r_squared: "R²", rmse: "RMSE", mae: "MAE", nrmse: "nRMSE", nse_pc: "NSE_PC" };
             
             let html = "<table style='width:100%; border-collapse:collapse; font-size:11px;'>";
             html += "<thead><tr style='background:#f5f5f5; border-bottom:2px solid #ccc;'>";
@@ -576,8 +576,8 @@
                 html += `<tr style='border-bottom:2px solid #ccc; background:#f9f9f9;'>`;
                 html += `<td style='padding:6px 8px; font-weight:600;'>S2 (baseline)</td>`;
                 metrics.forEach(m => {
-                    const val = data[m];
+                    const val = m === "nse_pc" ? (data.nse_pc ?? data.nse) : data[m];
-                    const fmt = val !== null && val !== undefined ? (m === "pearson_r" || m === "r_squared" || m === "nse" ? val.toFixed(3) : val.toFixed(4)) : "—";
+                    const fmt = val !== null && val !== undefined ? (m === "pearson_r" || m === "r_squared" || m === "nse_pc" ? val.toFixed(3) : val.toFixed(4)) : "—";
                     html += `<td style='padding:6px 8px; text-align:right; font-family:monospace;'>${fmt}</td>`;
                 });
                 html += "</tr>";
@@ -590,8 +590,8 @@
                 html += `<tr style='border-bottom:1px solid #eee;'>`;
                 html += `<td style='padding:6px 8px; font-weight:500;'>${scenarioNames[i]}</td>`;
                 metrics.forEach(m => {
-                    const val = data[m];
+                    const val = m === "nse_pc" ? (data.nse_pc ?? data.nse) : data[m];
-                    const fmt = val !== null && val !== undefined ? (m === "pearson_r" || m === "r_squared" || m === "nse" ? val.toFixed(3) : val.toFixed(4)) : "—";
+                    const fmt = val !== null && val !== undefined ? (m === "pearson_r" || m === "r_squared" || m === "nse_pc" ? val.toFixed(3) : val.toFixed(4)) : "—";
                     html += `<td style='padding:6px 8px; text-align:right; font-family:monospace;'>${fmt}</td>`;
                 });
                 html += "</tr>";

webapp/metrics.html

@@ -18,6 +18,7 @@
         th, td { border: 1px solid #ccc; padding: 6px 8px; text-align: left; }
         th { background: #f5f5f5; }
         td.num { text-align: right; font-variant-numeric: tabular-nums; }
+        .compare-note { font-size: 12px; color: #555; margin: 0 0 8px 0; max-width: 720px; }
         .empty { color: #666; font-style: italic; }
         .err { color: #a00; }
     </style>
@@ -42,7 +43,12 @@
         <div id="content"></div>
     </div>
     <script>
-        const METRIC_COLS = ["pearson_r", "r_squared", "rmse", "mae", "nrmse", "nse", "n_samples"];
+        const METRIC_COLS = ["pearson_r", "r_squared", "rmse", "mae", "nrmse", "nse_pc", "n_samples"];
+        /** Spatial fusion metrics in metrics.json (no RMSE block at site level). */
+        const SPATIAL_METRIC_COLS = ["pearson_r", "r_squared", "n_samples"];
+        function mv(m, c) {
+            return c === "nse_pc" ? (m.nse_pc ?? m.nse) : m[c];
+        }
         let siteName = "innsbruck", season = "2024";
         let availableSiteSeasons = {};
         const urlParams = new URLSearchParams(location.search);
@@ -67,11 +73,75 @@
             let head = `<tr><th>Scenario</th>${METRIC_COLS.map((c) => `<th>${c}</th>`).join("")}</tr>`;
             const rows = keys.map((k) => {
                 const m = obj[k] || {};
-                return `<tr><td>${k}</td>${METRIC_COLS.map((c) => `<td class="num">${fmt(m[c])}</td>`).join("")}</tr>`;
+                return `<tr><td>${k}</td>${METRIC_COLS.map((c) => `<td class="num">${fmt(mv(m, c))}</td>`).join("")}</tr>`;
             }).join("");
             return `<h2>${title}</h2><table>${head}${rows}</table>`;
         }
 
+        /** Pair BtI keys (`aggressive_sigma20`) with ItB (`aggressive_sigma20_itb`). */
+        function btiItbPairs(obj) {
+            if (!obj || typeof obj !== "object") return [];
+            const pairs = [];
+            for (const itbKey of Object.keys(obj)) {
+                if (!itbKey.endsWith("_itb")) continue;
+                const btiKey = itbKey.slice(0, -"_itb".length);
+                const bti = obj[btiKey];
+                const itb = obj[itbKey];
+                if (!bti || !itb) continue;
+                pairs.push({ label: btiKey, bti, itb });
+            }
+            pairs.sort((a, b) => a.label.localeCompare(b.label));
+            return pairs;
+        }
+
+        function fmtDelta(btiM, itbM, col) {
+            const a = mv(btiM, col);
+            const b = mv(itbM, col);
+            if (a == null || b == null || typeof a !== "number" || typeof b !== "number") return "—";
+            return fmt(b - a);
+        }
+
+        function btiItbCompareSection(title, obj, blurb, metricCols = METRIC_COLS) {
+            const pairs = btiItbPairs(obj);
+            if (!pairs.length) return "";
+            const subHead = metricCols.map(
+                () => `<th class="num">BtI</th><th class="num">ItB</th><th class="num">Δ</th>`
+            ).join("");
+            const head =
+                `<tr><th rowspan="2">Scenario</th>${metricCols.map((c) => `<th colspan="3">${c}</th>`).join("")}</tr>` +
+                `<tr>${subHead}</tr>`;
+            const rows = pairs
+                .map((p) => {
+                    const cells = metricCols.map((c) => {
+                        const vB = fmt(mv(p.bti, c));
+                        const vI = fmt(mv(p.itb, c));
+                        const d = fmtDelta(p.bti, p.itb, c);
+                        return `<td class="num">${vB}</td><td class="num">${vI}</td><td class="num">${d}</td>`;
+                    }).join("");
+                    return `<tr><td>${p.label}</td>${cells}</tr>`;
+                })
+                .join("");
+            return `<h2>${title}</h2><p class="compare-note">${blurb}</p><table>${head}${rows}</table>`;
+        }
+
+        function baselineSection(b) {
+            if (!b || typeof b !== "object") return "";
+            const rows = [];
+            const pushRow = (label, m) => {
+                if (!m || typeof m !== "object") return;
+                rows.push(`<tr><td>${label}</td>${METRIC_COLS.map((c) => `<td class="num">${fmt(mv(m, c))}</td>`).join("")}</tr>`);
+            };
+            pushRow("S2 GCC (all acquisitions)", b.s2);
+            for (const strat of ["aggressive", "nonaggressive"]) {
+                pushRow(`S3 composite GCC (${strat})`, b.s3?.[strat]);
+                pushRow(`S2 GCC cloud-screened (${strat})`, b.s2_cloudfree?.[strat]);
+                pushRow(`S2 Whittaker λ=400 (${strat})`, b.s2_whittaker_lambda400?.[strat]);
+            }
+            if (!rows.length) return "";
+            const head = `<tr><th>Baseline</th>${METRIC_COLS.map((c) => `<th>${c}</th>`).join("")}</tr>`;
+            return `<h2>Baselines (temporal vs PhenoCam)</h2><table>${head}${rows.join("")}</table>`;
+        }
+
         function render(data) {
             const el = document.getElementById("content");
             if (!data) {
@@ -84,12 +154,19 @@
                 const p = data.phenocam_stats;
                 html += `<td class="num">${fmt(p.mean)}</td><td class="num">${fmt(p.std)}</td><td class="num">${fmt(p.min)}</td><td class="num">${fmt(p.max)}</td><td class="num">${fmt(p.n_samples)}</td></tr></table>`;
             }
-            if (data.baseline && data.baseline.s2) {
+            html += baselineSection(data.baseline);
-                html += `<h2>Baseline S2 (temporal)</h2><table><tr>${METRIC_COLS.map((c) => `<th>${c}</th>`).join("")}</tr><tr>`;
+            html += btiItbCompareSection(
-                const b = data.baseline.s2;
+                "Temporal: BtI vs ItB (paired)",
-                html += METRIC_COLS.map((c) => `<td class="num">${fmt(b[c])}</td>`).join("") + "</tr></table>";
+                data.temporal,
-            }
+                "Δ = ItB − BtI. For Pearson r, R², and NSE (%), positive Δ means ItB is higher. For RMSE, MAE, and NRMSE, negative Δ means ItB is better (lower error)."
+            );
             html += tableSection("Temporal (vs PhenoCam)", data.temporal);
+            html += btiItbCompareSection(
+                "Spatial: BtI vs ItB (paired)",
+                data.spatial,
+                "Δ = ItB − BtI. For Pearson r and R², positive Δ means ItB is higher.",
+                SPATIAL_METRIC_COLS
+            );
             html += tableSection("Spatial (3×3 fusion mean vs PhenoCam)", data.spatial);
             if (data.summary) {
                 html += `<h2>Summary</h2><pre style="font-size:13px;background:#f9f9f9;padding:10px;">${JSON.stringify(data.summary, null, 2)}</pre>`;