Michael Sumner mdsumner

##  docker run --rm -ti ghcr.io/mdsumner/gdal-builds:rocker-gdal-dev-python bash
reticulate::use_python("/workenv/bin/python3")
library(reticulate)
py_require("virtualizarr")
open_virtual_mfdataset <- import("virtualizarr")$open_virtual_mfdataset
ds <- open_virtual_mfdataset(list("https://thredds.nci.org.au/thredds/fileServer/gb6/BRAN/BRAN2023/daily/atm_flux_diag_2024_06.nc"))

Spider worldclim for urls of useable data


library(bowerbird)
my_directory <- tempdir()
cf <- bb_config(local_file_root = my_directory)

##https://geodata.ucdavis.edu/climate/worldclim/2_1/base/wc2.1_10m_tmin.zip
src <-

reticulate::use_python("/workenv/bin/python3")
reticulate::py_require("numcodecs")
numcodecs <- reticulate::import("numcodecs")

## just found by eye
zlib <- numcodecs$zlib$Zlib(4L)

https://github.com/openlandmap/GEDTM30?tab=readme-ov-file

gdalinfo /vsicurl/https://s3.opengeohub.org/global/edtm/legendtm_rf_30m_m_s_20000101_20231231_go_epsg.4326_v20250130.tif

Driver: GTiff/GeoTIFF
Files: /vsicurl/https://s3.opengeohub.org/global/edtm/legendtm_rf_30m_m_s_20000101_20231231_go_epsg.4326_v20250130.tif
Size is 1440010, 600010
Coordinate System is:

x_from_col <- function(dimension, bbox, col) {
  col[col < 1] <- NA
  col[col > dimension[1L]] <- NA
  xres <- diff(bbox[c(1, 3)]) / dimension[1]
  bbox[1] - xres/2 + col * xres
}
y_from_row <- function(dimension, bbox, row) {
  row[row < 1] <- NA
  row[row > dimension[2]] <- NA

extract rema at points

library(xml2)
library(gdalraster)
dsn <- "/vsicurl/https://raw.githubusercontent.com/mdsumner/rema-ovr/main/REMA-2m_dem_ovr.vrt"
url <- gsub("/vsicurl/", "", dsn)
xml <- read_xml(url)
dst <- xml |> xml_find_all(".//DstRect")

## https://developmentseed.org/obstore/latest/examples/fastapi/

# Example large Parquet file hosted in AWS open data
#store = S3Store("ookla-open-data", region="us-west-2", skip_signature=True)
#path = "parquet/performance/type=fixed/year=2024/quarter=1/2024-01-01_performance_fixed_tiles.parquet"


Sys.setenv("AWS_REGION" = "us-west-2")

128 cpus, 158 seconds

options(parallelly.fork.enable = TRUE, future.rng.onMisuse = "ignore")
library(furrr); plan(multicore)
d <- arrow::read_parquet("https://data.source.coop/ausantarctic/ghrsst-mur-v2/ghrsst-mur-v2.parquet")
dsn <- sprintf("/vsicurl/%s", d$assets$analysed_sst$href)

#(cell <- terra::cellFromXY(terra::rast(dsn[1]), cbind(147, -48)))
# 496796700

Open a virtual dataset, how can I get the dict() of references from .lat?

import virtualizarr
oisst = virtualizarr.open_virtual_dataset("https://www.ncei.noaa.gov/data/sea-surface-temperature-optimum-interpolation/v2.1/access/avhrr/198109/oisst-avhrr-v02r01.19810901.nc")

oisst.lat
<xarray.DataArray 'lat' (lat: 720)> Size: 3kB
ManifestArray

	alg/data/2by2.tif
	alg/data/3by3_average.tif
	alg/data/3by3_sum.tif
	alg/data/4by4.tif
	alg/data/bug_6526_input.tif
	alg/data/contour_in.tif
	alg/data/geoloc/latitude_including_pole.tif
	alg/data/geoloc/longitude_including_pole.tif
	alg/data/nodata_precision_issue_float32.tif
	alg/data/pat.tif