Satellite Environmental MonitoringPemantauan Lingkungan Berbasis Satelit

 pip install earthchange

A hands-on tutorial. Map deforestation, mining, urbanisation, floods, burns and surface-water change anywhere on Earth from free satellite data — then export georeferenced GeoTIFFs and print-ready maps. All in Python, powered by Google Earth Engine and Microsoft Planetary Computer.

Tutorial praktis. Petakan deforestasi, tambang, urbanisasi, banjir, kebakaran, dan perubahan air permukaan di mana saja dari data satelit gratis — lalu ekspor GeoTIFF tergeoreferensi dan peta siap cetak. Semua dengan Python, ditenagai Google Earth Engine dan Microsoft Planetary Computer.

Why this existsMengapa perangkat lunak ini ada

Satellite data has been free for years. The ability to use it has not. The imagery is there — Sentinel, Landsat, MODIS, decades of it, downloadable by anyone. What stands between those images and an answer is a stack of things that take months to learn: cloud masking, projections, which index suits which question, what threshold deserves to be called "change", and how to turn a raster into a number someone can act on. Yet the people who most need the answer — a district forestry officer, an NGO researcher, a journalist on deadline, a lecturer preparing a class, a student with three months left — are often precisely the people without those months. So the question this package asks is a narrow one: can a single command do the whole thing?

Data satelit sudah gratis bertahun-tahun. Kemampuan memakainya belum. Citranya ada — Sentinel, Landsat, MODIS, berpuluh tahun, bisa diunduh siapa saja. Yang berdiri di antara citra itu dan sebuah jawaban adalah tumpukan hal yang perlu berbulan-bulan untuk dikuasai: penapisan awan, sistem proyeksi, indeks mana untuk pertanyaan mana, ambang berapa yang pantas disebut "berubah", dan bagaimana mengubah raster menjadi angka yang bisa ditindaklanjuti orang. Sementara mereka yang paling membutuhkan jawabannya — penyuluh kehutanan di kabupaten, peneliti lembaga swadaya, wartawan yang dikejar tenggat, dosen yang menyiapkan kuliah, mahasiswa yang tinggal punya tiga bulan — justru sering kali adalah orang-orang yang tidak punya bulan-bulan itu. Maka pertanyaan yang diajukan paket ini sempit saja: bisakah satu baris perintah mengerjakan seluruhnya?

A function you use again and againFungsi yang dipakai berulang-ulang

The answer this package gives is not a script you adapt. It is a ready-made analysis — the method, the thresholds, the masking and the output already decided — and the only things you change are where and when. Those two are the whole interface:

Jawaban yang diberikan paket ini bukan skrip yang harus Anda sesuaikan. Ia adalah analisis siap pakai — metode, ambang, penapisan, dan bentuk keluarannya sudah ditetapkan — dan yang Anda ubah hanyalah di mana dan kapan. Keduanya adalah seluruh antarmukanya:

# Ketapang, 2019
earthchange -s fire-danger --admin Ketapang --date 2019-09-30

# the same analysis, somewhere else, another year
earthchange -s fire-danger --admin "Kalimantan Tengah" --date 2026-08-01

Nothing was written between those two lines. No index chosen, no cloud mask configured, no projection set, no colour ramp designed. That is what "ready to use" has to mean if it is to be worth anything: copy, change two words, run — and out come a map you can put in front of a bupati, a GeoTIFF for the GIS staff, and a JSON of numbers for the report. A novice never opens a code editor.

Tidak ada satu baris pun yang ditulis di antara kedua perintah itu. Tidak memilih indeks, tidak menyetel penapis awan, tidak mengatur proyeksi, tidak merancang gradasi warna. Itulah yang harus berarti "siap pakai" agar ada gunanya: salin, ubah dua kata, jalankan — dan keluarlah peta yang bisa disodorkan kepada bupati, GeoTIFF untuk staf GIS, dan JSON angka untuk laporan. Pengguna pemula tidak pernah membuka editor kode.

This is deliberately not a toolbox. A general GIS platform hands you a thousand operations and asks which sequence answers your question; that is the right tool for someone who already knows the answer to that. This is for the far larger group who have the question but not the method — who need to know whether a district is drying, not which spectral index to subtract from which. Both kinds of software should exist. They are not substitutes.

Ini memang sengaja bukan kotak perkakas. Platform GIS umum menyodorkan seribu operasi lalu bertanya urutan mana yang menjawab pertanyaan Anda; itu perkakas yang tepat bagi orang yang sudah tahu jawabannya. Yang ini untuk kelompok yang jauh lebih besar — mereka yang punya pertanyaannya tetapi bukan metodenya, yang perlu tahu apakah sebuah kabupaten sedang mengering, bukan indeks spektral mana yang harus dikurangkan dari mana. Keduanya perlu ada. Keduanya bukan pengganti satu sama lain.

One honest wrinkle. "Just change the date" holds completely for a season that has ended. For anything recent it does not: the archives run between one day and three months behind, each by a different amount, so the newest date that works shifts daily and differs by scenario. The package will tell you which date to use rather than fail obscurely — but it is the one part of the copy-and-paste promise that needs a little care.

Satu catatan jujur. "Tinggal ganti tanggalnya" berlaku sepenuhnya untuk musim yang sudah berakhir. Untuk data terkini tidak: arsipnya tertinggal antara satu hari sampai tiga bulan, masing-masing berbeda, sehingga tanggal terbaru yang bisa dipakai bergeser tiap hari dan berbeda antar skenario. Paket ini akan memberi tahu tanggal mana yang bisa dipakai, bukan gagal tanpa penjelasan — tetapi inilah satu bagian dari janji salin-tempel yang perlu sedikit kehati-hatian.

ObjectivesTujuan

• One command, one question. No Earth Engine scripting, no threshold to choose, no projections to manage.
• Calibrated where it runs. Fire danger classes follow BMKG, not Canada. Day-length factors use the equatorial convention, because the standard tables were drawn up for 46°N. Drought Code leads over FWI, because peat fire is driven by deep drying. Air quality uses ISPU. Global tools are calibrated for everywhere, which means for nowhere in particular.
• Outputs you can actually use. A print-ready A4 map sheet, a GeoTIFF that opens straight in QGIS, statistics as JSON, and text in Indonesian and English.
• Your own data, not only global layers. Rice-field boundaries, forest designation, an authoritative peat map — crossed with public satellite data. That is the difference between "West Kalimantan is dry" and "87% of this nature reserve is dry".
• Honest about its limits. Every output states what it cannot tell you. A tool that hides its limits misleads precisely when it is trusted most.
• Free, open and citable. MIT licence, Zenodo DOI.

• Satu perintah untuk satu pertanyaan. Tidak perlu menulis skrip Earth Engine, tidak perlu memilih ambang, tidak perlu mengurus proyeksi.
• Dikalibrasi di tempat ia dipakai. Ambang bahaya kebakaran mengikuti BMKG, bukan Kanada. Faktor panjang hari memakai konvensi ekuatorial, karena tabel bakunya disusun untuk 46°LU. Drought Code dipimpinkan di atas FWI, karena kebakaran gambut didorong pengeringan lapisan dalam. Kualitas udara memakai ISPU. Perkakas global dikalibrasi untuk seluruh dunia — yang berarti tidak untuk tempat mana pun secara khusus.
• Keluaran yang benar-benar bisa dipakai. Lembar peta A4 siap cetak, GeoTIFF yang langsung terbuka di QGIS, statistik JSON, teks dwibahasa.
• Data Anda sendiri, bukan hanya data global. Lahan baku sawah, batas fungsi kawasan, peta gambut resmi — disilangkan dengan data satelit publik. Inilah yang membedakan "Kalimantan Barat kering" dari "87% cagar alam ini kering".
• Jujur tentang batasnya. Tiap keluaran menyebutkan apa yang tidak bisa ia katakan. Perangkat yang menyembunyikan batasnya akan menyesatkan tepat pada saat ia paling dipercaya.
• Gratis, terbuka, dapat disitasi. Lisensi MIT, DOI Zenodo.

The hopeHarapan

The measure of this package is not downloads. It is whether an analysis that would never have happened, happens — because the person who needed to answer the question no longer had to become a remote sensing specialist first. A lecturer teaches with it. A student finishes a thesis with it. An organisation publishes a number that others can check. A district official sees which areas are drying, before they burn. And a further hope: that people take this approach to their own places. BMKG's thresholds suit Indonesia and nowhere else, but the idea that a tool should be calibrated for where it is used — and should say what it does not know — travels anywhere.

Ukuran keberhasilan paket ini bukan jumlah unduhan. Ukurannya adalah apakah ada analisis yang tadinya tidak akan pernah terjadi, akhirnya terjadi — karena orang yang perlu menjawab pertanyaannya tidak lagi harus lebih dulu menjadi ahli penginderaan jauh. Seorang dosen memakainya untuk mengajar. Seorang mahasiswa menyelesaikan skripsinya dengannya. Sebuah lembaga menerbitkan angka yang bisa diperiksa orang lain. Seorang pejabat kabupaten melihat kawasan mana yang sedang mengering, sebelum ia terbakar. Dan harapan yang lebih jauh: bahwa orang mengambil pendekatan ini untuk tempat mereka sendiri. Ambang BMKG hanya cocok untuk Indonesia, tetapi gagasan bahwa sebuah perkakas harus dikalibrasi untuk tempat ia dipakai — dan harus mengatakan apa yang tidak diketahuinya — berlaku di mana saja.

1 · What you'll buildYang akan Anda buat

By the end you'll run a single command like this…

Di akhir tutorial, Anda menjalankan satu perintah seperti ini…

earthchange -s deforestation --lat -3.333 --lon 122.25 --radius 6 --map

…and get three things for your chosen area:

…dan mendapat tiga berkas untuk area pilihan Anda:

• a quick-look PNG of the change,
• a full-resolution, georeferenced GeoTIFF you can open in QGIS/ArcGIS, and
• a value-added map (A4 PDF + PNG) with legend, scale bar, statistics and a location inset.

Cloud and shadow are the main source of false positives, and the direction is not random: shadow depresses NIR more than SWIR, so it lowers both NDVI and NBR — it mimics vegetation loss and burn, never gain. Per-pixel cloud masking plus a median over many scenes absorbs most of that, but a median over one clear look simply reproduces whatever the mask missed. Change is therefore only reported where both windows have at least --min-obs cloud-free looks at that pixel (default 2); the excluded share is printed and recorded in stats.clear_observations. Raise it to 3–4 in persistently cloudy areas, --min-obs 1 to disable. What this does not fix: a pixel with many looks that are all shadowed the same way — seasonal terrain shadow, for instance — passes the count test and still biases the result.

Awan dan bayangan adalah sumber utama positif palsu, dan arahnya tidak acak: bayangan menurunkan NIR lebih besar daripada SWIR, sehingga menurunkan NDVI maupun NBR — ia menyerupai kehilangan vegetasi dan kebakaran, tidak pernah pertambahan. Mask awan per piksel plus median banyak scene meredam sebagian besar hal itu, tetapi median dari satu pengamatan bersih hanya mengulang apa pun yang lolos dari mask. Karena itu perubahan hanya dilaporkan bila kedua jendela punya minimal --min-obs pengamatan bebas awan pada piksel tersebut (bawaan 2); porsi yang dikecualikan dicetak dan dicatat di stats.clear_observations. Naikkan ke 3–4 di wilayah yang terus berawan, --min-obs 1 untuk menonaktifkan. Yang belum teratasi: piksel dengan banyak pengamatan yang semuanya terbayang dengan cara sama — misalnya bayangan topografi musiman — lolos uji jumlah dan tetap membiaskan hasil.

Optical scenarios also write a SWIR false-colour quick-look of each source composite — the pre and post imagery the change was measured between — and record every scene that went into them (id, date, cloud %) under images_used in stats.json. A count alone can be neither checked nor reproduced; the ids can. Use --no-preview to skip both.

• PNG pratinjau perubahan,
• GeoTIFF resolusi penuh tergeoreferensi yang bisa dibuka di QGIS/ArcGIS, dan
• peta value-added (A4 PDF + PNG) dengan legenda, skala, statistik, dan inset lokasi.

Skenario optik juga menuliskan pratinjau warna semu SWIR untuk tiap komposit sumber — citra pra dan pasca yang menjadi dasar pengukuran perubahan — serta mencatat setiap scene yang menyusunnya (id, tanggal, % awan) pada images_used di stats.json. Jumlah scene saja tidak bisa diperiksa maupun direproduksi; id-nya bisa. Pakai --no-preview untuk melewati keduanya.

You pick a scenario (what kind of change) and a location (a coordinate). The tool selects the right remote-sensing method automatically. No prior GIS coding required.

Anda memilih skenario (jenis perubahan) dan lokasi (koordinat). Alat memilih metode penginderaan jauh yang tepat secara otomatis. Tanpa perlu pengalaman pemrograman GIS.

2 · How it works (the science)Cara kerjanya (sainsnya)

“Change detection” compares the landscape at two (or more) points in time and highlights what changed. Different phenomena leave different spectral or radar fingerprints, so each scenario uses a purpose-built index or method:

“Deteksi perubahan” membandingkan bentang lahan pada dua (atau lebih) titik waktu dan menonjolkan apa yang berubah. Fenomena berbeda meninggalkan sidik jari spektral atau radar yang berbeda, sehingga tiap skenario memakai indeks atau metode khusus:

How clouds are handledCara menangani awan

Optical scenarios never rely on a single image. For each period the tool builds a cloud-masked median composite of many Sentinel-2 scenes: every scene is masked pixel-by-pixel using the Scene Classification (SCL) band, then the median is taken. The result is effectively cloud-free even in cloudy regions. The standalone Sentinel-2 downloader additionally prefers a single scene with ≤10% cloud, falling back to the composite when none exists.

Skenario optik tak pernah bergantung pada satu citra. Untuk tiap periode, alat menyusun median composite bebas awan dari banyak scene Sentinel-2: tiap scene di-mask per-piksel memakai band Scene Classification (SCL), lalu diambil mediannya. Hasilnya praktis bebas awan bahkan di wilayah berawan. Pengunduh Sentinel-2 mandiri juga mengutamakan satu scene dengan awan ≤10%, dan beralih ke composite bila tak ada.

3 · SetupPersiapan

You need Python 3.11+. The Earth Engine backend needs a free Google Earth Engine account (sign up); the Planetary Computer backend needs no account at all.

Anda memerlukan Python 3.11+. Backend Earth Engine butuh akun Google Earth Engine gratis (daftar); backend Planetary Computer tanpa akun sama sekali.

1. Install the packagePasang paket

   pip install 'earthchange[all]'          # everything
   # or leaner:  pip install 'earthchange[gee]'  ·  pip install 'earthchange[mpc,maps]'

   Gives you the earthchange and earthmap commands. To work from source instead: git clone https://github.com/firmanhadi21/rs-change-detection && cd rs-change-detection && pip install -e '.[all]' — then python3 detect.py … works identically. Memberi perintah earthchange dan earthmap. Untuk memakai dari sumber: git clone https://github.com/firmanhadi21/rs-change-detection && cd rs-change-detection && pip install -e '.[all]' — lalu python3 detect.py … berfungsi sama.
2. Authenticate Earth Engine (GEE backend only)Autentikasi Earth Engine (backend GEE saja)

   earthengine authenticate

   Opens a browser to link your Google account. To use a service-account key from any directory, point earthchange at it with --ee-key /path/to/ee-geodetic.json, or export EARTHCHANGE_EE_KEY=/path/to/ee-geodetic.json, or copy it to ~/.config/earthengine/ee-geodetic.json. (A key at ./scripts/config/ee-geodetic.json only works when you run from the repo root.) Skip this entirely with --backend mpc. Membuka browser untuk menautkan akun Google. Untuk memakai kunci service account dari direktori mana pun, arahkan earthchange dengan --ee-key /path/ke/ee-geodetic.json, atau export EARTHCHANGE_EE_KEY=/path/ke/ee-geodetic.json, atau salin ke ~/.config/earthengine/ee-geodetic.json. (Kunci di ./scripts/config/ee-geodetic.json hanya berlaku saat dijalankan dari root repo.) Lewati dengan --backend mpc.
3. Check it's workingCek berjalan

   earthchange --list

   Should print the eighteen available scenarios. Harusnya menampilkan delapan belas skenario.

4 · Your first detectionDeteksi pertama Anda

Let's map vegetation loss around a coordinate. Pick any lat/lon (decimal degrees; south and west are negative).

Mari petakan kehilangan vegetasi di sekitar koordinat. Pilih lat/lon apa saja (derajat desimal; selatan dan barat negatif).

earthchange -s deforestation --lat -3.333 --lon 122.25 --radius 6

The tool builds a square area of interest (half-side = radius km), makes a cloud-free Sentinel-2 NDVI composite for a baseline year and a recent year, subtracts them, and downloads the result. You'll see something like:

Alat membangun area minat persegi (setengah-sisi = radius km), membuat composite NDVI Sentinel-2 bebas awan untuk tahun dasar dan tahun terkini, menguranginya, lalu mengunduh hasilnya. Anda akan melihat kira-kira:

=== Change detection: deforestation ===
Location: -3.333, 122.25  radius 6.0 km  [m3p333_122p25]
Downloading dndvi PNG...    Saved: images/deforestation_dndvi_m3p333_122p25.png
Downloading dndvi GeoTIFF... Saved: data/deforestation_dndvi_m3p333_122p25.tif
=== Results ===
  "pct_affected": 6.3, "pct_severe": 2.7, "scenes_pre": 30, "scenes_post": 25 …

5 · Reading the outputsMembaca keluaran

For optical scenarios the change layer uses a diverging palette: red = loss, pale = little change, green = gain. The stats.json quantifies it — e.g. pct_affected is the share of the area whose change passed the threshold.

Untuk skenario optik, layer perubahan memakai palet divergen: merah = kehilangan, pucat = sedikit berubah, hijau = pertambahan. stats.json mengukurnya — mis. pct_affected adalah proporsi area yang perubahannya melewati ambang.

6 · Every scenarioSetiap skenario

Which need an Earth Engine accountMana yang perlu akun Earth Engine

Not every scenario needs the same access, and it is worth knowing which before you start. There is no automatic fallback: --backend defaults to gee, and without credentials the run stops with instructions rather than quietly switching data source.

Tidak semua skenario memerlukan akses yang sama, dan ada baiknya mengetahuinya sebelum mulai. Tidak ada peralihan otomatis: --backend bawaannya gee, dan tanpa kredensial proses berhenti dengan petunjuk, bukan diam-diam berpindah sumber data.

If you have no Earth Engine account, the eight in the middle row plus smoke-video are available immediately — nine of the twenty-four. Everything in the fire-and-smoke chain needs an account, because the weather and air-quality archives it is built on live only there.

Bila Anda belum punya akun Earth Engine, delapan skenario di baris tengah ditambah smoke-video langsung bisa dipakai — sembilan dari dua puluh empat. Seluruh rantai kebakaran-asap memerlukan akun, sebab arsip cuaca dan kualitas udara yang menjadi dasarnya hanya ada di sana.

List them any time with earthchange --list. Commands:

Lihat daftarnya kapan saja dengan earthchange --list. Perintah:

# Deforestation / vegetation loss (default baseline vs recent year)
earthchange -s deforestation --lat -3.333 --lon 122.25

# Mining — radar temporal (SIRAD) + NDVI loss, two products
earthchange -s mining --lat -3.333 --lon 122.25
#   set the 3 SIRAD periods (R/G/B) yourself with --epochs:
earthchange -s mining --lat -3.333 --lon 122.25 \
    --epochs 2024-01-01:2024-06-30,2024-07-01:2024-12-31,2025-01-01:2025-06-30

# Urbanisation — built-up (NDBI) gain
earthchange -s urbanization --lat -6.2 --lon 106.8 --radius 12

# Surface-water change (NDWI)
earthchange -s water --lat -0.5 --lon 117.1

# Flood — needs an explicit baseline and event window
earthchange -s flood --lat 27.2 --lon 68.3 \
    --pre 2022-07-01:2022-07-25 --post 2022-08-20:2022-09-10

# Disturbance — flood/landslide impact in terrain, when flood shows nothing
earthchange -s disturbance --lat 1.9983 --lon 99.4235 --radius 15 \
    --pre 2025-11-01:2025-11-11 --post 2025-11-26:2025-11-29 --map

# Burn severity — needs pre-fire and post-fire windows
earthchange -s burn --lat -7.5 --lon 110.4 \
    --pre 2025-08-01:2025-08-20 --post 2025-09-10:2025-09-30

# Urban growth timing across 3 epochs (Landsat; default 2010/2015/2020)
earthchange -s urban-trend --lat -6.30 --lon 107.15 --radius 10 --map

# Urban history: built-up by decade since 1980 (GHSL + Landsat), whole metro
earthchange -s urban-history --lat -6.2 --lon 106.85 --radius 45 -n jabodetabek

# Hybrid: auto-locate the most-changed hotspot + a PlanetScope ~3 m close-up
earthchange -s urban-history --lat -6.2 --lon 106.85 --radius 45 --planet   # dry-run (free)

# Coastline: shoreline change (SAR) — erosion & accretion between two dates
earthchange -s coastline --lat -6.95 --lon 110.45 --radius 8 \
    --pre 2016-01-01:2016-12-31 --post 2025-01-01:2025-12-31

# Coastline time-series + retreat-rate transects (Landsat, back to the 1990s)
earthchange -s coastline --coast-method landsat --lat -6.95 --lon 110.45 --radius 10 \
    --epochs 1994-01-01:1996-12-31,2014-01-01:2016-12-31,2023-01-01:2025-12-31

# Custom cross-shore transects drawn in QGIS (clean m/yr in complex bays)
earthchange -s coastline --coast-method landsat --city "Pekalongan" --radius 12 \
    --epochs 1994-01-01:1996-12-31,2014-01-01:2016-12-31,2023-01-01:2025-12-31 \
    --transects-file my_transects.geojson

# Public-transport access (SDG 11.2.1): % population within a walk of a stop
earthchange -s transit-access --city "Semarang" --radius 8 --walk-dist 500,1000
# ...or supply your own stops/routes (e.g. a BRT corridor exported from QGIS)
earthchange -s transit-access --city "Semarang" --radius 10 \
    --transit-file transjateng_stops.geojson

# Island heat: SST + LST + wet-bulb trends + decadal change maps
earthchange -s island-heat --lat -0.657 --lon 130.234 --radius 40 \
    --lst-source modis -n "Raja Ampat"        # larger islands → MODIS LST
earthchange -s island-heat --lat -5.7 --lon 106.55 --radius 35 \
    -n "Kepulauan Seribu"                     # tiny islands → Landsat (default)

# Urban heat island: SUHII + hot-spot map + decadal trend
earthchange -s urban-heat --lat -6.20 --lon 106.83 --radius 18 -n "Jakarta"
earthchange -s urban-heat --city "Surabaya" --radius 15 --months 6-9   # dry-season only

# Multi-epoch deforestation: when was each patch of forest cleared? (Landsat, 1990→2024)
earthchange -s forest-history --sensor landsat --lat -2.2 --lon 113.0 --radius 12 \
    --epochs 1990-01-01:1992-12-31,2000-01-01:2002-12-31,2010-01-01:2012-12-31,2017-01-01:2019-12-31,2023-01-01:2025-12-31

# Population change 1990→2020 — Miloš-style city-spike poster on shaded terrain
earthchange -s population-change --bbox 105,-8.9,114.6,-5.8 --cell-km 1 -n Jawa
#   whole country, per main island, assembled into one panel:
earthchange -s population-change --country Indonesia --regions indonesia --cell-km 5
#   plus a true GPU 3D render (needs pip install 'earthchange[forge3d]'):
earthchange -s population-change --bbox 105,-8.9,114.6,-5.8 --cell-km 5 -n Jawa --forge3d

# Fire history — burned area per year, recurrence map, fire season
earthchange -s fire-history --admin Riau                     # real province polygon
earthchange -s fire-history --lat 0.5 --lon 101.9 --radius 60 --start-year 2001
#   peat split: soil-carbon proxy (default), PEATGRIDS, or a real peat map
earthchange -s fire-history --admin Riau --peat-source peatgrids
earthchange -s fire-history --admin Riau --peat-file TROP-SUBTROP_PeatV21_2016_CIFOR.tif
#   compare several areas, and rank the current season against history
earthchange -s fire-history --areas "Riau,Jambi,Sumatera Selatan" --vs-baseline

# Smoke exposure — person-days by ISPU class, per district, split by age
earthchange -s smoke-exposure --bbox 108.8,-4.3,119.0,2.2 -n Kalimantan \
  --season 2019-08-01:2019-11-30 --pop-year 2019

# Where the smoke went — indicative air-parcel fan (illustration, not attribution)
#   needs: pip install 'earthchange[track]'
earthchange -s smoke-track --bbox 108.8,-4.3,117.0,2.2 -n Kalimantan \
  --date 2019-09-15 --track-hours 48
#   the defensible version: real HYSPLIT trajectories on GDAS1
#   needs the free hyts_std binary; GDAS1 is fetched from public S3 and cached
earthchange -s smoke-track --bbox 108.8,-4.3,117.0,2.2 -n Kalimantan \
  --date 2019-09-15 --engine hysplit --track-heights 100,500,1500
#   and the question that has to survive challenge: where did this air come from?
earthchange -s smoke-track --bbox 108.8,-4.3,117.0,2.2 -n Kalimantan \
  --date 2019-09-15 --engine hysplit --direction backward --track-parcels 12

# Wildfire smoke animation — no Earth Engine account needed (last 7 days only)
#   needs: pip install 'earthchange[video]' + ffmpeg + a Vulkan device
earthchange -s smoke-video --lat -1.85 --lon 110.0 -n Ketapang \
  --video-cities "Ketapang,109.977,-1.839,major; Sukadana,109.950,-1.250"

# Fire-season accountability record — one reproducible record per land designation
#   --zones is YOUR OWN layer: nothing is bundled. For Indonesia, the forest
#   designation layer (SK Penunjukan Kawasan Hutan) comes from KLHK.
earthchange -s fire-record --admin Ketapang --season 2019-07-01:2019-11-30 \
  --zones /path/to/your/forest.gpkg --zone-field FUNGSI_HTN

# Fire danger — Canadian FWI System from ERA5-Land weather
earthchange -s fire-danger --admin "Kalimantan Barat"
#   rate a specific day (default: freshest complete ERA5-Land day, ~6 days back)
earthchange -s fire-danger --lat -1.85 --lon 110.0 -r 50 -n Ketapang --fdrs-end 2015-09-30
#   longer accumulation after a prolonged dry spell
earthchange -s fire-danger --admin Riau --spinup 90

# Imagery — just the data: a 6-band GeoTIFF and previews, no change detection
#   one specific date
earthchange -s imagery --lat -7.54 --lon 110.45 --radius 8 -n Merapi --date 2025-07-11
#   or a cloud-free median composite over a window
earthchange -s imagery --city "Palangka Raya, Indonesia" -r 15 --date 2025-07-01:2025-08-31
#   Landsat instead, for anything before 2015 — give it a wide window:
#   Landsat 5 revisited equatorial Indonesia rarely, and most passes were cloudy
earthchange -s imagery --lat -7.54 --lon 110.45 --date 2010-01-01:2010-12-31 --sensor landsat

# Drought — rainfall deficit, vegetation health, and whether ENSO is driving it
earthchange -s drought --lat -10.18 --lon 123.60 --radius 40 -n Kupang
earthchange -s drought --admin "Nusatenggara Timur"           # GAUL spelling: no space
#   CHIRPS lags ~5 weeks; use a fresher product to see a season in progress
earthchange -s drought --admin "Jawa Tengah" --rain-source era5
earthchange -s drought --admin "Jawa Tengah" --rain-source imerg
#   3 months = agricultural framing (default); 6-12 = hydrological
earthchange -s drought --admin "Jawa Timur" --spi-months 6
#   pin the window end instead of tracking the latest CHIRPS image
earthchange -s drought --lat -7.25 --lon 112.75 --drought-end 2026-06-30
#   combine meteorological + agricultural + vegetation into one classified map
earthchange -s drought --admin "Sulawesi Selatan" --rain-source imerg --cdi
#   ...and read it only on the rice, with exact hectares per class
earthchange -s drought --admin "Sulawesi Selatan" --rain-source imerg --cdi \
  --cdi-mask LBS_SULSEL_50m.tif --cdi-mask-name "rice fields" --cdi-grid 500

# Haze — smoke and the air people actually breathe, during a fire episode
earthchange -s haze --lat -2.21 --lon 113.92 --radius 30 -n "Palangka Raya"
earthchange -s haze --admin "Kalimantan Tengah" --haze-start 2026-07-01 --haze-end 2026-07-29

# Island heat with a one-page story poster (Indonesian + English)
earthchange -s island-heat --lat -0.66 --lon 130.23 --radius 40 \
    -n "Raja Ampat" --lst-source modis --infographic --lang both

7 · Make a map productMembuat produk peta

Add --map to any run to render an A4-landscape map sheet (PDF + PNG) per product: OpenStreetMap basemap, the change layer, title, legend, a statistics panel, a location inset, coordinate grid, scale bar and north arrow.

Tambahkan --map pada run apa pun untuk membuat lembar peta A4 landscape (PDF + PNG) per produk: basemap OpenStreetMap, layer perubahan, judul, legenda, panel statistik, inset lokasi, grid koordinat, skala, dan panah utara.

earthchange -s mining --lat -3.333 --lon 122.25 --map

Already have results and just want to re-render (no Earth Engine needed)? Every run drops a .meta.json sidecar, so:

Sudah punya hasil dan ingin render ulang (tanpa Earth Engine)? Tiap run menulis sidecar .meta.json, jadi:

earthmap output/20260708-2226_deforestation_x_fac24e   # a run folder
earthmap output/<run>/mining_sirad_x.tif --basemap gray  # or one .tif

Maps land in maps/. Tweak the layout in mapmaker.py and re-run instantly.

Peta tersimpan di maps/. Ubah tata letak di mapmaker.py lalu jalankan ulang seketika.

8 · Adapt it to your own areaMenyesuaikan untuk area Anda

Pick a locationPilih lokasi

Find coordinates by right-clicking a spot in Google Maps (it copies lat, lon), or from OpenStreetMap. Choose a --radius to match the feature: a few km for a single mine or town, 10–20 km for a flood plain or a fire.

Cari koordinat dengan klik kanan di Google Maps (menyalin lat, lon), atau dari OpenStreetMap. Pilih --radius sesuai objek: beberapa km untuk satu tambang atau kota, 10–20 km untuk dataran banjir atau kebakaran.

Save a named presetSimpan preset bernama

Add reusable places to sites.py and call them with --site:

Tambahkan lokasi yang sering dipakai ke sites.py dan panggil dengan --site:

SITES = {
  "my_area": {
    "label": "My study area",
    "lat": 1.234, "lon": 103.456, "radius_km": 8.0,
    "sentinel2_date": "2026-06-15",
    "sirad_periods": [("2024-01-01","2024-12-31"),
                      ("2025-01-01","2025-12-31"),
                      ("2026-01-01","2026-06-30")],
    "ndvi_pre":  ("2023-01-01","2023-12-31"),
    "ndvi_post": ("2026-01-01","2026-06-30"),
  },
}

earthchange -s deforestation --site my_area --map

Add a brand-new scenarioTambah skenario baru

Most scenarios are one dictionary entry in scenarios.py. To add, say, a moisture-change scenario using NDWI on a custom threshold you only add a registry entry — the generic optical-change engine does the rest:

Kebanyakan skenario hanya satu entri dictionary di scenarios.py. Untuk menambah, misalnya, skenario perubahan kelembapan memakai NDWI dengan ambang khusus, cukup tambahkan satu entri — mesin perubahan optik generik menangani sisanya:

"moisture": {
    "label": "Moisture change (NDWI)",
    "run": _optical("NDWI", "gain", 0.08, 0.20),  # index, direction, thresholds
    "radius": 10.0, "needs": "pre_post",
    "pre":  ("2023-01-01","2023-12-31"),
    "post": ("2025-01-01","2025-12-31"),
    "interpretation": "Greener = wetter.",
},

New spectral indices go in indices.py (a one-line normalised difference). Radar or bespoke methods get a small run_* function in scenarios.py.

Indeks spektral baru masuk ke indices.py (satu baris normalized difference). Metode radar atau khusus memakai fungsi run_* kecil di scenarios.py.

9 · Reproducibility & dataReproduksibilitas & data

• Data: Copernicus Sentinel-1 (radar) and Sentinel-2 (optical), free and open, courtesy ESA, processed in Google Earth Engine.
• AOI: a square centred on your coordinate (half-side = radius), axis-aligned in EPSG:4326.
• Orbit auto-selection: radar scenarios check both ascending and descending orbits and use whichever has imagery in every period.
• Outputs are regenerable, so results and maps are git-ignored; only code and this tutorial are versioned.

• Data: Copernicus Sentinel-1 (radar) dan Sentinel-2 (optik), gratis dan terbuka, dari ESA, diproses di Google Earth Engine.
• AOI: persegi berpusat di koordinat Anda (setengah-sisi = radius), sejajar sumbu di EPSG:4326.
• Pemilihan orbit otomatis: skenario radar memeriksa orbit ascending dan descending lalu memakai yang punya citra di tiap periode.
• Keluaran bisa dibuat ulang, jadi hasil dan peta di-git-ignore; hanya kode dan tutorial ini yang diversikan.

10 · TroubleshootingPemecahan masalah

11 · Further readingBacaan lanjut

• Zha, Gao & Ni (2003). Use of NDBI in automatically mapping urban areas from TM imagery. Int. J. Remote Sensing 24(3).
• Key & Benson (2006). Landscape Assessment: the Normalized Burn Ratio (NBR/dNBR). USDA Forest Service, FIREMON.
• UN-SPIDER. Recommended Practice: Flood Mapping with Sentinel-1 SAR in Google Earth Engine.
• UN-SPIDER. Normalized Burn Ratio — in detail.
• Earth Lab. Work with the Differenced Normalized Burn Index (dNBR).
• Google Earth Engine. Sentinel-1 SAR guide · Sentinel-2 SR Harmonized.