"""Build the shared TrendeX data cube (F1) from the downloaded NASA rasters. python scripts/20_build_cube.py # everything python scripts/20_build_cube.py --only static # cells.parquet only (terrain, land cover, districts) Master grid = the global MODIS sinusoidal 1 km grid, cut to the request area (aoi_request.geojson). NDVI is never resampled (same grid -> nearest = copy). Other layers: 500 m / 30 m -> average or mode, 0.1 / 0.25 deg weather -> bilinear at cell centres. Each MODIS/NASADEM layer is read from AppEEARS GeoTIFFs when that AppEEARS task finished, otherwise from raw LP DAAC files fetched with earthaccess (HDF4 tiles / NASADEM zips). manifest.json records which. Outputs in data/cube/: cells.parquet one row per 1 km cell inside the request area monthly/year=YYYY/*.parquet one row per cell x month manifest.json inputs, sources, counts, scale checks, notes """ from __future__ import annotations import argparse import calendar import json import re import time from concurrent.futures import ProcessPoolExecutor from pathlib import Path import geopandas as gpd import numpy as np import pandas as pd import pyarrow as pa import pyarrow.parquet as pq import rasterio import xarray as xr from pyproj import Transformer from rasterio.warp import Resampling, reproject from scipy.ndimage import uniform_filter from shapely import contains_xy ROOT = Path("/root/trendex-ml/data") RAW, AOI_DIR, OUT = ROOT / "raw", ROOT / "aoi", ROOT / "cube" PAT = re.compile(r"^(?P[A-Z0-9_]+\.\d{3})_(?P.+)_doy(?P\d{7})_aid(?P\d{4})\.tif$") BLOCK = 11 # 11 x 11 cells ~ 10.2 km blocks (F5, spatial CV) STEEP_DEG = 35.0 # "too steep" default; to be agreed with the formula owner (F1) TPI_WINDOW = 5 # cells (~5 km) for the topographic position index WORKERS = 32 SINU = "+proj=sinu +lon_0=0 +x_0=0 +y_0=0 +R=6371007.181 +units=m +no_defs" SINU_CRS = rasterio.crs.CRS.from_proj4(SINU) TILE = 1111950.5196666666 # MODIS tile size, m X0, Y0 = -20015109.355798, 10007554.677899 # upper-left corner of the global MODIS grid PIX1K = TILE / 1200 # Raw HDF4 tiles (LP DAAC fallback): layer key -> (SDS name, pixels per tile side) HDF_SDS = { "MOD13A3": {"NDVI": ("1 km monthly NDVI", 1200), "pixel_reliability": ("1 km monthly pixel reliability", 1200)}, "MYD13A3": {"NDVI": ("1 km monthly NDVI", 1200), "pixel_reliability": ("1 km monthly pixel reliability", 1200)}, "MOD11A2": {k: (k, 1200) for k in ("LST_Day_1km", "LST_Night_1km", "QC_Day", "QC_Night")}, "MOD10A2": {"Maximum_Snow_Extent": ("Maximum_Snow_Extent", 2400)}, "MCD12Q1": {"LC_Type1": ("LC_Type1", 2400), "LW": ("LW", 2400)}, } GRID: dict = {} # filled in main(), read by worker processes after fork SOURCES_USED: dict = {} # ----------------------------------------------------------------------------- sources def appeears_done(product: str) -> bool: marker = RAW / "appeears_done.json" return marker.exists() and json.loads(marker.read_text()).get(product) == "done" def appeears_index(product: str) -> pd.DataFrame: rows = [] for p in sorted((RAW / "appeears" / product).glob("*.tif")): m = PAT.match(p.name) if not m: continue year, doy = int(m["doy"][:4]), int(m["doy"][4:]) date = pd.Timestamp(year=year, month=1, day=1) + pd.Timedelta(days=doy - 1) rows.append({"path": str(p), "layer": m["layer"], "date": date}) if not rows: raise SystemExit(f"AppEEARS marked {product} done but no GeoTIFFs matched {PAT.pattern}") return pd.DataFrame(rows) def sources(product: str, layer: str) -> dict: """date -> list of raster sources for one layer (AppEEARS if finished, else raw LP DAAC files).""" if appeears_done(product): idx = appeears_index(product) idx = idx[idx["layer"].str.endswith(layer)] SOURCES_USED[product] = "AppEEARS" return {d: g["path"].tolist() for d, g in idx.groupby("date")} folder = RAW / "earthaccess" / product if product == "NASADEM": tiles = sorted(folder.glob("*.zip")) if not tiles: raise SystemExit("No NASADEM data from AppEEARS (not finished) or LP DAAC") SOURCES_USED[product] = "LP DAAC (earthaccess)" return {pd.Timestamp("2000-02-11"): [f"/vsizip/{z}/{z.stem.split('_')[-1]}.hgt" for z in tiles]} hdfs = sorted(folder.glob("*.hdf")) if not hdfs: raise SystemExit(f"No {product} data from AppEEARS (not finished) or LP DAAC ({folder})") SOURCES_USED[product] = "LP DAAC (earthaccess)" sds, npix = HDF_SDS[product][layer] by_date: dict = {} for p in hdfs: m = re.search(r"\.A(\d{4})(\d{3})\.", p.name) d = pd.Timestamp(year=int(m[1]), month=1, day=1) + pd.Timedelta(days=int(m[2]) - 1) by_date.setdefault(d, []).append(("hdf", str(p), sds, npix)) return dict(sorted(by_date.items())) def flat(d: dict) -> list: return [x for v in d.values() for x in v] def _open(src): """-> (raw array, nodata, transform, crs) for a GDAL path or an ('hdf', path, sds, npix) tuple.""" if isinstance(src, str): with rasterio.open(src) as s: return s.read(1), s.nodata, s.transform, s.crs _, path, sds, npix = src from pyhdf.SD import SD, SDC m = re.search(r"\.h(\d{2})v(\d{2})\.", Path(path).name) h, v = int(m[1]), int(m[2]) f = SD(path, SDC.READ) try: ds = f.select(sds) raw, attrs = ds.get(), ds.attributes() finally: f.end() pix = TILE / npix return raw, attrs.get("_FillValue"), rasterio.transform.from_origin(X0 + h * TILE, Y0 - v * TILE, pix, pix), SINU_CRS # ----------------------------------------------------------------------------- grid helpers def build_master_grid() -> dict: minx, miny, maxx, maxy = gpd.read_file(AOI_DIR / "aoi_request.geojson").to_crs(SINU).total_bounds c0, c1 = int(np.floor((minx - X0) / PIX1K)), int(np.ceil((maxx - X0) / PIX1K)) r0, r1 = int(np.floor((Y0 - maxy) / PIX1K)), int(np.ceil((Y0 - miny) / PIX1K)) left, top = X0 + c0 * PIX1K, Y0 - r0 * PIX1K return {"crs": SINU_CRS, "transform": rasterio.transform.from_origin(left, top, PIX1K, PIX1K), "shape": (r1 - r0, c1 - c0), "res": (PIX1K, PIX1K), "left": left, "top": top, "global_row0": r0, "global_col0": c0} def _nodata_to_nan(raw: np.ndarray, nodata) -> np.ndarray: a = raw.astype("float32") if nodata is not None: a[raw == nodata] = np.nan return a def to_master(srcs: list, resampling: Resampling, fn=None) -> np.ndarray: """Mosaic all pieces (AppEEARS area pieces or MODIS tiles) of one layer/date onto the master grid. fn(raw_array, nodata) -> float32 array with NaN for invalid pixels. Default: nodata -> NaN. """ out = np.full(GRID["shape"], np.nan, dtype="float32") for src in srcs: raw, nodata, transform, crs = _open(src) a = fn(raw, nodata) if fn else _nodata_to_nan(raw, nodata) tmp = np.full(GRID["shape"], np.nan, dtype="float32") reproject(a.astype("float32"), tmp, src_transform=transform, src_crs=crs, dst_transform=GRID["transform"], dst_crs=GRID["crs"], resampling=resampling, src_nodata=np.nan, dst_nodata=np.nan) out = np.where(np.isnan(out), tmp, out) return out def autoscale(a: np.ndarray, scale: float, raw_if_above: float) -> tuple[np.ndarray, bool]: """Raw HDF4 is never scaled; AppEEARS output may or may not be. Decide from the data and record it.""" m = np.nanmax(a) if np.isfinite(a).any() else 0 return (a * scale, True) if m > raw_if_above else (a, False) # ----------------------------------------------------------------------------- per-date workers def ndvi_date(args) -> tuple: date, ndvi_src, rel_src = args ndvi, scaled = autoscale(to_master(ndvi_src, Resampling.nearest), 1e-4, 1.5) rel = to_master(rel_src, Resampling.nearest) if rel_src else np.full(GRID["shape"], np.nan, "float32") return date, ndvi.astype("float32"), rel.astype("float32"), scaled def _lst(raw, nodata): a = raw.astype("float32") a[(raw == 0) | ((nodata is not None) & (raw == nodata))] = np.nan return a def lst_date(args) -> tuple: date, day_src, night_src, qcd_src, qcn_src = args out = [] for vals, qcs in ((day_src, qcd_src), (night_src, qcn_src)): t, _ = autoscale(to_master(vals, Resampling.nearest, fn=_lst), 0.02, 1000) qc = to_master(qcs, Resampling.nearest, fn=lambda r, nd: r.astype("float32")) good = np.isfinite(qc) & ((np.nan_to_num(qc).astype("uint8") & 3) <= 1) # bits 0-1: 00 good, 01 other out.append(np.where(good, t - 273.15, np.nan).astype("float32")) return date, out[0], out[1] def _snow(raw, nodata): # MOD10A2 Maximum_Snow_Extent: 200 snow, 25 no snow; everything else invalid a = np.full(raw.shape, np.nan, "float32") a[raw == 200] = 1.0 a[raw == 25] = 0.0 return a def snow_date(args) -> tuple: date, srcs = args return date, to_master(srcs, Resampling.average, fn=_snow) # ----------------------------------------------------------------------------- static layers def static_layers(rc: tuple[np.ndarray, np.ndarray]) -> dict: r, c = rc out = {} lc_p, lw_p = flat(sources("MCD12Q1", "LC_Type1")), flat(sources("MCD12Q1", "LW")) out["lc_type1"] = to_master(lc_p, Resampling.mode, fn=lambda raw, nd: np.where(raw == 255, np.nan, raw).astype("float32"))[r, c] for name, cls in {"grass_frac": 10, "ice_frac": 15, "urban_frac": 13, "barren_frac": 16}.items(): out[name] = to_master(lc_p, Resampling.average, fn=lambda raw, nd, k=cls: np.where(raw == 255, np.nan, raw == k).astype("float32"))[r, c] out["water_frac"] = to_master(lw_p, Resampling.average, fn=lambda raw, nd: np.where(raw == 255, np.nan, raw == 1).astype("float32"))[r, c] acc = {k: np.full(GRID["shape"], np.nan, "float32") for k in ("z", "z2", "slope", "steep", "asin", "acos")} for src in flat(sources("NASADEM", "NASADEM_HGT")): # slope on the native 30 m grid first, then average raw, nodata, tr, crs = _open(src) z = _nodata_to_nan(raw, nodata if nodata is not None else -32768) lat = tr.f + tr.e * (np.arange(z.shape[0]) + 0.5) dy = abs(tr.e) * 111_320.0 dx = tr.a * 111_320.0 * np.cos(np.deg2rad(lat))[:, None] gy_rows, gx_cols = np.gradient(z) gx, gy = gx_cols / dx, -gy_rows / dy # east, north slope = np.degrees(np.arctan(np.hypot(gx, gy))).astype("float32") aspect = np.arctan2(-gx, -gy) # downslope direction, clockwise from north layers = {"z": z, "z2": z * z, "slope": slope, "steep": np.where(np.isnan(slope), np.nan, slope > STEEP_DEG).astype("float32"), "asin": np.sin(aspect).astype("float32"), "acos": np.cos(aspect).astype("float32")} for k, arr in layers.items(): tmp = np.full(GRID["shape"], np.nan, "float32") reproject(arr.astype("float32"), tmp, src_transform=tr, src_crs=crs, dst_transform=GRID["transform"], dst_crs=GRID["crs"], resampling=Resampling.average, src_nodata=np.nan, dst_nodata=np.nan) acc[k] = np.where(np.isnan(acc[k]), tmp, acc[k]) elev = acc["z"] out["elev_mean"] = elev[r, c] out["elev_std"] = np.sqrt(np.clip(acc["z2"] - elev ** 2, 0, None))[r, c] out["slope_mean"], out["steep_share"] = acc["slope"][r, c], acc["steep"][r, c] out["aspect_sin"], out["aspect_cos"] = acc["asin"][r, c], acc["acos"][r, c] valid = np.isfinite(elev) num = uniform_filter(np.where(valid, elev, 0), TPI_WINDOW) den = uniform_filter(valid.astype("float32"), TPI_WINDOW) out["tpi"] = (elev - num / np.maximum(den, 1e-6))[r, c] return out def mask_reason(df: pd.DataFrame) -> pd.Series: reason = pd.Series(pd.NA, index=df.index, dtype="string") rules = [("water", (df["water_frac"] > 0.5) | (df["lc_type1"] == 17)), ("ice", df["lc_type1"] == 15), ("urban", df["lc_type1"] == 13), ("too_steep", df["slope_mean"] > STEEP_DEG)] for name, cond in rules: # first matching rule wins reason = reason.mask(reason.isna() & cond.fillna(False), name) return reason # ----------------------------------------------------------------------------- weather (GES DISC) def weather(cells: pd.DataFrame) -> pd.DataFrame: lon = xr.DataArray(cells["lon"].values, dims="cell") lat = xr.DataArray(cells["lat"].values, dims="cell") pad = 0.5 lo0, lo1 = float(lon.min()) - pad, float(lon.max()) + pad la0, la1 = float(lat.min()) - pad, float(lat.max()) + pad ids = cells["cell_id"].values frames = [] for p in sorted((RAW / "gesdisc" / "GPM_3IMERGM").glob("*.HDF5")): ym = re.search(r"\.(\d{8})-S", p.name).group(1) y, m = int(ym[:4]), int(ym[4:6]) with xr.open_dataset(p, group="Grid", engine="h5netcdf") as ds: da = ds["precipitation"].squeeze(drop=True).sel(lon=slice(lo0, lo1), lat=slice(la0, la1)).load() mm_month = da.interp(lon=lon, lat=lat) * 24 * calendar.monthrange(y, m)[1] # mm/hr -> mm/month frames.append(pd.DataFrame({"cell_id": ids, "year": y, "month": m, "precip": mm_month.values.astype("float32")})) precip = pd.concat(frames, ignore_index=True) frames = [] for p in sorted((RAW / "gesdisc" / "GLDAS_NOAH025_M").glob("*.nc4")): ym = re.search(r"\.A(\d{6})\.", p.name).group(1) y, m = int(ym[:4]), int(ym[4:]) with xr.open_dataset(p) as ds: sub = ds[["SoilMoi0_10cm_inst", "SWE_inst"]].squeeze(drop=True).sel( lon=slice(lo0, lo1), lat=slice(la0, la1)).load() pts = sub.interp(lon=lon, lat=lat) frames.append(pd.DataFrame({"cell_id": ids, "year": y, "month": m, "soil_moist": pts["SoilMoi0_10cm_inst"].values.astype("float32"), "swe": pts["SWE_inst"].values.astype("float32")})) gldas = pd.concat(frames, ignore_index=True) return precip.merge(gldas, on=["cell_id", "year", "month"], how="outer") # ----------------------------------------------------------------------------- main def monthly_mean(dated: list[tuple], r, c) -> dict: """Average 8-day composites into calendar months (by composite start date).""" groups: dict = {} for date, arr in dated: groups.setdefault((date.year, date.month), []).append(arr[r, c]) with np.errstate(all="ignore"): return {k: np.nanmean(np.stack(v), axis=0).astype("float32") for k, v in groups.items()} def build_cells() -> tuple[pd.DataFrame, np.ndarray, np.ndarray]: nrow, ncol = GRID["shape"] rr, cc = np.meshgrid(np.arange(nrow), np.arange(ncol), indexing="ij") x = GRID["left"] + (cc + 0.5) * PIX1K y = GRID["top"] - (rr + 0.5) * PIX1K lon, lat = Transformer.from_crs(GRID["crs"], 4326, always_xy=True).transform(x, y) aoi = gpd.read_file(AOI_DIR / "aoi_request.geojson").to_crs(4326) region = np.full(x.shape, "", dtype=object) for _, f in aoi.iterrows(): region[(region == "") & contains_xy(f.geometry, lon, lat)] = f["name"] keep = region != "" r, c = rr[keep], cc[keep] cells = pd.DataFrame({ # global MODIS row/col -> stable id that does not depend on our crop "cell_id": ((r + GRID["global_row0"]) * 43200 + (c + GRID["global_col0"])).astype("int64"), "row": r, "col": c, "x": x[keep], "y": y[keep], "lon": lon[keep], "lat": lat[keep], "region": region[keep].astype(str), "block_id": [f"{a}-{b}" for a, b in zip(r // BLOCK, c // BLOCK)], "block_row": (r // BLOCK).astype("int16"), "block_col": (c // BLOCK).astype("int16")}) dist = gpd.read_file(AOI_DIR / "naryn_districts.geojson").to_crs(4326) cells["district"] = pd.Series(pd.NA, index=cells.index, dtype="string") for _, d in dist.iterrows(): cells.loc[contains_xy(d.geometry, cells["lon"].values, cells["lat"].values), "district"] = d["shapeName"] cells["in_oblast"] = cells["district"].notna() adm1 = gpd.read_file(AOI_DIR / "geoBoundaries-KGZ-ADM1.geojson").to_crs(4326) gb = adm1[adm1["shapeName"].str.contains("Naryn")].geometry.iloc[0] cells["in_adm1_naryn"] = contains_xy(gb, cells["lon"].values, cells["lat"].values) cells["boundary_conflict"] = cells["in_oblast"] != cells["in_adm1_naryn"] return cells, r, c def write_monthly(cells, ndvi, rel, aqua, lst_day, lst_night, snow, wx) -> list[int]: """One parquet file per year under monthly/year=YYYY/ (hive layout: pd.read_parquet(dir) adds `year`).""" nan = np.full(len(cells), np.nan, "float32") ids = cells["cell_id"].values years = sorted({y for y, _ in ndvi}) for yr in years: parts = [] for m in range(1, 13): k = (yr, m) if k not in ndvi: continue rk = rel.get(k, nan) cols = {"cell_id": ids, "year": yr, "month": m, "ndvi": ndvi[k], "ndvi_rel": rk, "ndvi_ok": np.isin(rk, (0, 1)), "ndvi_aqua": aqua.get(k, nan)} if wx is not None: cols |= {"lst_day": lst_day.get(k, nan), "lst_night": lst_night.get(k, nan), "snow": snow.get(k, nan)} parts.append(pd.DataFrame(cols)) df = pd.concat(parts, ignore_index=True) if wx is not None: df = df.merge(wx[wx["year"] == yr], on=["cell_id", "year", "month"], how="left") df["month"] = df["month"].astype("int8") dest = OUT / "monthly" / f"year={yr}" dest.mkdir(parents=True, exist_ok=True) pq.write_table(pa.Table.from_pandas(df.drop(columns=["year"]), preserve_index=False), dest / "part.parquet") return years def main() -> None: global GRID ap = argparse.ArgumentParser() ap.add_argument("--only", choices=["static", "all"], default="all") args = ap.parse_args() t0 = time.time() OUT.mkdir(parents=True, exist_ok=True) manifest: dict = {"created_utc": time.strftime("%Y-%m-%dT%H:%M:%SZ", time.gmtime()), "synthetic": False, "partial": True, "units": {"ndvi": "NDVI (scaled, -0.2..1)", "ndvi_rel": "MOD13A3 pixel reliability (0 good, 1 marginal, 2 snow/ice, 3 cloud)", "ndvi_ok": "bool, reliability 0 or 1", "ndvi_aqua": "NDVI from MYD13A3, reliability 0-1 only", "lst_day": "deg C, monthly mean of QA-good 8-day MOD11A2", "lst_night": "deg C", "snow": "fraction 0-1 of 8-day MOD10A2 periods with snow (Mar-Sep only)", "precip": "mm per month (IMERG Final V07, mm/hr x 24 x days)", "soil_moist": "kg m-2 in 0-10 cm (GLDAS-2.1 Noah)", "swe": "kg m-2 (GLDAS-2.1 Noah)", "elev_mean": "m", "slope_mean": "deg", "steep_share": f"share of 30 m pixels steeper than {STEEP_DEG} deg", "lc_type1": "IGBP class (MCD12Q1 LC_Type1, 2020), mode over 500 m pixels"}, "datasets": {"MOD13A3": "061, doi:10.5067/MODIS/MOD13A3.061", "MYD13A3": "061, doi:10.5067/MODIS/MYD13A3.061", "MOD11A2": "061, doi:10.5067/MODIS/MOD11A2.061", "MOD10A2": "61, doi:10.5067/MODIS/MOD10A2.061", "MCD12Q1": "061, doi:10.5067/MODIS/MCD12Q1.061", "NASADEM_HGT": "001, doi:10.5067/MEaSUREs/NASADEM/NASADEM_HGT.001", "GPM_3IMERGM": "07, doi:10.5067/GPM/IMERG/3B-MONTH/07", "GLDAS_NOAH025_M": "2.1, doi:10.5067/SXAVCZFAQLNO"}, "notes": ["Oblast = 5 official districts (geoBoundaries ADM2). geoBoundaries ADM1 'Naryn Region' " "disagrees (adds Toguz-Toro, misses ~1,900 km2 of Jumgal near Suusamyr); such cells " "have boundary_conflict=true.", f"mask_reason 'too_steep' uses slope_mean > {STEEP_DEG} deg (default, to be agreed)."]} GRID = build_master_grid() manifest["grid"] = {"crs": SINU, "shape": GRID["shape"], "res_m": PIX1K, "origin_left_top": [GRID["left"], GRID["top"]], "block_cells": BLOCK, "cell_id": "global_row * 43200 + global_col on the MODIS 1 km grid"} print(f"master grid {GRID['shape']} ({PIX1K:.3f} m)", flush=True) cells, r, c = build_cells() for k, v in static_layers((r, c)).items(): cells[k] = v cells["mask_reason"] = mask_reason(cells) cells.to_parquet(OUT / "cells.parquet", index=False) manifest["cells"] = {"n": len(cells), "in_oblast": int(cells["in_oblast"].sum()), "by_region": cells["region"].value_counts().astype(int).to_dict(), "mask_reason_counts": {str(k): int(v) for k, v in cells["mask_reason"].value_counts(dropna=False).items()}} print(f"cells: {len(cells)} ({cells['in_oblast'].sum()} in oblast) {time.time() - t0:.0f}s", flush=True) if args.only == "static": manifest["sources_used"] = dict(SOURCES_USED) (OUT / "manifest.json").write_text(json.dumps(manifest, indent=2, default=str)) print("STATIC_DONE", flush=True) return ndvi, rel, aqua, scaled_flags = {}, {}, {}, set() with ProcessPoolExecutor(WORKERS) as pool: nd, nr = sources("MOD13A3", "NDVI"), sources("MOD13A3", "pixel_reliability") for d, a, b, s in pool.map(ndvi_date, [(d, nd[d], nr.get(d, [])) for d in nd]): ndvi[(d.year, d.month)], rel[(d.year, d.month)] = a[r, c], b[r, c] scaled_flags.add(s) ad, ar = sources("MYD13A3", "NDVI"), sources("MYD13A3", "pixel_reliability") for d, a, b, _ in pool.map(ndvi_date, [(d, ad[d], ar.get(d, [])) for d in ad]): aqua[(d.year, d.month)] = np.where(np.isin(b[r, c], (0, 1)), a[r, c], np.nan) print(f"ndvi: {len(ndvi)} months, aqua: {len(aqua)} {time.time() - t0:.0f}s", flush=True) write_monthly(cells, ndvi, rel, aqua, {}, {}, {}, None) manifest["sources_used"] = dict(SOURCES_USED) manifest["monthly"] = {"columns": ["cell_id", "year", "month", "ndvi", "ndvi_rel", "ndvi_ok", "ndvi_aqua"], "note": "PARTIAL: NDVI only; weather/LST/snow columns follow in the full build"} (OUT / "manifest.json").write_text(json.dumps(manifest, indent=2, default=str)) print("PARTIAL_NDVI_DONE", flush=True) L = {k: sources("MOD11A2", k) for k in ("LST_Day_1km", "LST_Night_1km", "QC_Day", "QC_Night")} jobs = [(d, L["LST_Day_1km"][d], L["LST_Night_1km"].get(d, []), L["QC_Day"].get(d, []), L["QC_Night"].get(d, [])) for d in L["LST_Day_1km"]] res = list(pool.map(lst_date, jobs)) lst_day = monthly_mean([(d, a) for d, a, _ in res], r, c) lst_night = monthly_mean([(d, b) for d, _, b in res], r, c) sn = sources("MOD10A2", "Maximum_Snow_Extent") snow = monthly_mean(list(pool.map(snow_date, list(sn.items()))), r, c) print(f"lst: {len(lst_day)} months, snow: {len(snow)} months {time.time() - t0:.0f}s", flush=True) manifest["ndvi_scale_applied_by_us"] = sorted(scaled_flags) manifest["sources_used"] = dict(SOURCES_USED) wx = weather(cells) print(f"weather rows: {len(wx)} {time.time() - t0:.0f}s", flush=True) years = write_monthly(cells, ndvi, rel, aqua, lst_day, lst_night, snow, wx) manifest["partial"] = False manifest["monthly"] = {"years": [years[0], years[-1]], "months_ndvi": len(ndvi), "months_aqua": len(aqua), "months_lst": len(lst_day), "months_snow": len(snow), "weather_rows": int(len(wx))} manifest["inputs"] = {f"{base.name}/{p.name}": len(list(p.glob("*"))) for base in (RAW / "appeears", RAW / "earthaccess", RAW / "gesdisc") if base.exists() for p in base.iterdir() if p.is_dir()} (OUT / "manifest.json").write_text(json.dumps(manifest, indent=2, default=str)) print(f"CUBE_DONE {time.time() - t0:.0f}s", flush=True) if __name__ == "__main__": main()