How unit 5 is examined
This unit covers four application areas: land cover and land use mapping, environmental monitoring, disaster management and precision agriculture. None was asked in the supplied papers, so each is taught as a compact definition, key points, formula and worked example.
Land cover and land use mapping
<span style="display:inline-block;padding:.16em .6em;border:1.5px solid currentColor;border-radius:999px;font-size:.68em;font-weight:700;letter-spacing:.06em;text-transform:uppercase;opacity:.75">Not asked since 2022</span>
Definition. <mark>Land cover is the physical material on the ground (water, forest, soil, built-up), while land use is the human purpose of that land (farming, housing, industry); LULC mapping classifies every satellite pixel into such classes.</mark>
Diagram.
<figure class="ds-fig" style="margin:1.4rem 0;overflow-x:auto"><svg xmlns="http://www.w3.org/2000/svg" id="dsfig-u5-01" viewBox="0 0 603 209" width="603" height="209" role="img" aria-label="LULC workflow: Img satellite image, Pre correction, Feat bands and indices, Clf classifier, Map land cover map, Acc accuracy check"><style>#dsfig-u5-01 .e{stroke:#454C5A;stroke-width:1.4;fill:none}#dsfig-u5-01 .e.hi{stroke:#2340B8;stroke-width:2.6}#dsfig-u5-01 .n{fill:#FFFFFF;stroke:#16181D;stroke-width:1.4}#dsfig-u5-01 .n.hi{fill:#E3E9FC;stroke:#2340B8;stroke-width:2.2}#dsfig-u5-01 .n.rb-b{fill:#16181D;stroke:#16181D}#dsfig-u5-01 .n.rb-r{fill:#BD3227;stroke:#BD3227}#dsfig-u5-01 text{font-family:"JetBrains Mono",ui-monospace,Menlo,Consolas,monospace;font-size:13px}#dsfig-u5-01 .t{fill:#16181D;font-weight:500}#dsfig-u5-01 .t.inv{fill:#FFFFFF;font-weight:700}#dsfig-u5-01 .kd{stroke:#16181D;stroke-width:1.2}#dsfig-u5-01 .dot{fill:#16181D}#dsfig-u5-01 .ann{fill:#2340B8;font-size:11px;font-weight:700}#dsfig-u5-01 .lbl{fill:#6F7787;font-family:system-ui,-apple-system,sans-serif;font-size:12px;font-weight:700}#dsfig-u5-01 .ptr{fill:#2340B8;font-size:12px;font-weight:700}#dsfig-u5-01 .ah{fill:#454C5A}#dsfig-u5-01 .ah.hi{fill:#2340B8}#dsfig-u5-01 .wl rect{fill:#FFFFFF;stroke:#DCE0E7}#dsfig-u5-01 .wl .t{font-size:12px;font-weight:700}#dsfig-u5-01 .wl.hi rect{fill:#2340B8;stroke:#2340B8}#dsfig-u5-01 .wl.hi .t{fill:#FFFFFF}html.dark #dsfig-u5-01 .e{stroke:#B1B7C3}html.dark #dsfig-u5-01 .e.hi{stroke:#8FA3FF}html.dark #dsfig-u5-01 .n{fill:#161920;stroke:#E6E8ED}html.dark #dsfig-u5-01 .n.hi{fill:#1E2748;stroke:#8FA3FF}html.dark #dsfig-u5-01 .n.rb-b{fill:#E6E8ED;stroke:#E6E8ED}html.dark #dsfig-u5-01 .n.rb-r{fill:#FF7E71;stroke:#FF7E71}html.dark #dsfig-u5-01 .t{fill:#E6E8ED}html.dark #dsfig-u5-01 .t.inv{fill:#0F1115}html.dark #dsfig-u5-01 .kd{stroke:#E6E8ED}html.dark #dsfig-u5-01 .dot{fill:#E6E8ED}html.dark #dsfig-u5-01 .ann{fill:#8FA3FF}html.dark #dsfig-u5-01 .lbl{fill:#858D9C}html.dark #dsfig-u5-01 .ptr{fill:#8FA3FF}html.dark #dsfig-u5-01 .ah{fill:#B1B7C3}html.dark #dsfig-u5-01 .ah.hi{fill:#8FA3FF}html.dark #dsfig-u5-01 .wl rect{fill:#161920;stroke:#2A2E37}html.dark #dsfig-u5-01 .wl.hi rect{fill:#8FA3FF;stroke:#8FA3FF}html.dark #dsfig-u5-01 .wl.hi .t{fill:#0F1115}</style><defs><marker id="ah13" viewBox="0 0 10 10" refX="9" refY="5" markerWidth="7" markerHeight="7" orient="auto-start-reverse"><path class="ah" d="M0,1 L9,5 L0,9 z"/></marker><marker id="ahh13" viewBox="0 0 10 10" refX="9" refY="5" markerWidth="7" markerHeight="7" orient="auto-start-reverse"><path class="ah hi" d="M0,1 L9,5 L0,9 z"/></marker></defs><path class="e" d="M59,40 L148,40" marker-end="url(#ah13)"/><path class="e" d="M188,40 L270,40" marker-end="url(#ah13)"/><path class="e" d="M324,40 L406,40" marker-end="url(#ah13)"/><path class="e" d="M446,40 L535,40" marker-end="url(#ah13)"/><path class="e" d="M542.6,53.4 L441.8,154.2" marker-end="url(#ah13)"/><circle class="n" cx="40" cy="40" r="18"/><text class="t" x="40" y="40" dy=".35em" text-anchor="middle">Img</text><circle class="n" cx="169" cy="40" r="18"/><text class="t" x="169" y="40" dy=".35em" text-anchor="middle">Pre</text><rect class="n" x="273" y="25" width="50" height="30" rx="15"/><text class="t" x="298" y="40" dy=".35em" text-anchor="middle">Feat</text><circle class="n" cx="427" cy="40" r="18"/><text class="t" x="427" y="40" dy=".35em" text-anchor="middle">Clf</text><circle class="n" cx="556" cy="40" r="18"/><text class="t" x="556" y="40" dy=".35em" text-anchor="middle">Map</text><circle class="n" cx="427" cy="169" r="18"/><text class="t" x="427" y="169" dy=".35em" text-anchor="middle">Acc</text></svg><figcaption style="font-size:.82em;opacity:.72;margin-top:.45rem">LULC workflow: Img satellite image, Pre correction, Feat bands and indices, Clf classifier, Map land cover map, Acc accuracy check</figcaption></figure>
Key points.
- Land cover is observed directly from the spectral signature of the surface, but land use must be inferred from context, shape and neighbouring objects.
- Classifiers such as random forest, SVM and CNNs (for example U-Net for semantic segmentation) label each pixel or patch using multispectral bands and indices.
- Training samples come from ground truth or high-resolution imagery, and the map is checked on separate test samples.
- Accuracy is reported with a confusion matrix, overall accuracy and the kappa coefficient.
- Maps of different years are compared to detect change, such as urban sprawl, deforestation or loss of wetlands.
- Typical uses are urban planning, water resource management, forest inventory and policy reporting.
Formula. Overall accuracy $OA = \frac{\text{correct pixels}}{\text{total pixels}}$ and $\kappa = \frac{p_o - p_e}{1 - p_e}$, where $p_o$ is observed agreement and $p_e$ is chance agreement.
Example. A 2-class test (water, land) with 100 samples: 45 water and 40 land correct, 5 water called land, 10 land called water. $p_o = 85/100 = 0.85$; row totals are 50 and 50, column totals 55 and 45, so $p_e = (50 \times 55 + 50 \times 45)/100^2 = 0.50$; $\kappa = (0.85-0.50)/0.50 = 0.70$. OA = 85%, kappa = 0.70.
Comparison.
| Basis | Land cover | Land use |
|---|---|---|
| Meaning | Physical surface material | Human purpose of the land |
| Example | Forest, water, bare soil | Plantation, reservoir, mining site |
| Source | Read directly from spectral signature | Inferred from context, shape and ancillary data |
| Change speed | Changes with vegetation and season | Changes with policy and development |
| Typical AI method | Pixel classifiers, indices | CNN or object-based classifiers with GIS layers |
Common classes. Water, built-up, cropland, forest, grassland, barren land and wetland are the usual classes; agencies such as NRSC use a nested scheme so that each class splits into finer sub-classes.
Pitfall. Do not call a mixed pixel a single class without saying so: coarse pixels blend several covers, which lowers accuracy at class boundaries.
Environmental monitoring and assessment
<span style="display:inline-block;padding:.16em .6em;border:1.5px solid currentColor;border-radius:999px;font-size:.68em;font-weight:700;letter-spacing:.06em;text-transform:uppercase;opacity:.75">Not asked since 2022</span>
Definition. <mark>Environmental monitoring uses repeated satellite observations, analysed by AI, to measure the condition of water, air, vegetation and ecosystems and to assess how they change over time.</mark>
Key points.
- Water bodies, turbidity and algal blooms are mapped with spectral indices such as $NDWI = \frac{Green - NIR}{Green + NIR}$, where open water gives positive values.
- Forest cover loss and vegetation health are tracked using NDVI time series and deep-learning change detection.
- Air pollutants and greenhouse gases such as aerosols, NO2 and CO2 are retrieved from satellite sensors and modelled with regression or neural networks.
- Thermal bands give land surface temperature, which supports urban heat island and drought studies.
- Glacier retreat, wetland shrinkage, coastal erosion and mining impact are monitored over areas that ground surveys cannot cover.
- AI helps by processing long archives automatically, filling cloud gaps and flagging anomalies for inspectors.
Example. A lake pixel has Green 0.10 and NIR 0.03, so $NDWI = (0.10-0.03)/(0.10+0.03) = 0.54$, which is above zero and is classed as water. NDWI = 0.54.
Common indicators.
| Concern | Indicator or data | Sensor |
|---|---|---|
| Vegetation health | NDVI, EVI | Optical multispectral |
| Surface water | NDWI, SAR backscatter | Optical, radar |
| Air quality | Aerosol optical depth, NO2 column | Atmospheric sensors |
| Heat and drought | Land surface temperature | Thermal infrared |
| Forest loss | NDVI drop between dates | Multi-date optical |
Answer frame. Open with the definition of environmental monitoring; list the four themes (water, vegetation, air, heat) with one index each; give the NDWI or NDVI example; close by saying that AI automates long time-series analysis over large areas.
Disaster management and response
<span style="display:inline-block;padding:.16em .6em;border:1.5px solid currentColor;border-radius:999px;font-size:.68em;font-weight:700;letter-spacing:.06em;text-transform:uppercase;opacity:.75">Not asked since 2022</span>
Definition. <mark>Disaster management uses remote sensing and AI to predict, detect, map and assess hazards such as floods, fires, earthquakes, landslides and cyclones, so that preparedness and rescue are faster.</mark>
Diagram.
<figure class="ds-fig" style="margin:1.4rem 0;overflow-x:auto"><svg xmlns="http://www.w3.org/2000/svg" id="dsfig-u5-02" viewBox="0 0 544.4 80" width="544.4" height="80" role="img" aria-label="Disaster cycle: Prd prediction and early warning, Det detection, Map damage mapping, Rsp response and recovery"><style>#dsfig-u5-02 .e{stroke:#454C5A;stroke-width:1.4;fill:none}#dsfig-u5-02 .e.hi{stroke:#2340B8;stroke-width:2.6}#dsfig-u5-02 .n{fill:#FFFFFF;stroke:#16181D;stroke-width:1.4}#dsfig-u5-02 .n.hi{fill:#E3E9FC;stroke:#2340B8;stroke-width:2.2}#dsfig-u5-02 .n.rb-b{fill:#16181D;stroke:#16181D}#dsfig-u5-02 .n.rb-r{fill:#BD3227;stroke:#BD3227}#dsfig-u5-02 text{font-family:"JetBrains Mono",ui-monospace,Menlo,Consolas,monospace;font-size:13px}#dsfig-u5-02 .t{fill:#16181D;font-weight:500}#dsfig-u5-02 .t.inv{fill:#FFFFFF;font-weight:700}#dsfig-u5-02 .kd{stroke:#16181D;stroke-width:1.2}#dsfig-u5-02 .dot{fill:#16181D}#dsfig-u5-02 .ann{fill:#2340B8;font-size:11px;font-weight:700}#dsfig-u5-02 .lbl{fill:#6F7787;font-family:system-ui,-apple-system,sans-serif;font-size:12px;font-weight:700}#dsfig-u5-02 .ptr{fill:#2340B8;font-size:12px;font-weight:700}#dsfig-u5-02 .ah{fill:#454C5A}#dsfig-u5-02 .ah.hi{fill:#2340B8}#dsfig-u5-02 .wl rect{fill:#FFFFFF;stroke:#DCE0E7}#dsfig-u5-02 .wl .t{font-size:12px;font-weight:700}#dsfig-u5-02 .wl.hi rect{fill:#2340B8;stroke:#2340B8}#dsfig-u5-02 .wl.hi .t{fill:#FFFFFF}html.dark #dsfig-u5-02 .e{stroke:#B1B7C3}html.dark #dsfig-u5-02 .e.hi{stroke:#8FA3FF}html.dark #dsfig-u5-02 .n{fill:#161920;stroke:#E6E8ED}html.dark #dsfig-u5-02 .n.hi{fill:#1E2748;stroke:#8FA3FF}html.dark #dsfig-u5-02 .n.rb-b{fill:#E6E8ED;stroke:#E6E8ED}html.dark #dsfig-u5-02 .n.rb-r{fill:#FF7E71;stroke:#FF7E71}html.dark #dsfig-u5-02 .t{fill:#E6E8ED}html.dark #dsfig-u5-02 .t.inv{fill:#0F1115}html.dark #dsfig-u5-02 .kd{stroke:#E6E8ED}html.dark #dsfig-u5-02 .dot{fill:#E6E8ED}html.dark #dsfig-u5-02 .ann{fill:#8FA3FF}html.dark #dsfig-u5-02 .lbl{fill:#858D9C}html.dark #dsfig-u5-02 .ptr{fill:#8FA3FF}html.dark #dsfig-u5-02 .ah{fill:#B1B7C3}html.dark #dsfig-u5-02 .ah.hi{fill:#8FA3FF}html.dark #dsfig-u5-02 .wl rect{fill:#161920;stroke:#2A2E37}html.dark #dsfig-u5-02 .wl.hi rect{fill:#8FA3FF;stroke:#8FA3FF}html.dark #dsfig-u5-02 .wl.hi .t{fill:#0F1115}</style><defs><marker id="ah14" viewBox="0 0 10 10" refX="9" refY="5" markerWidth="7" markerHeight="7" orient="auto-start-reverse"><path class="ah" d="M0,1 L9,5 L0,9 z"/></marker><marker id="ahh14" viewBox="0 0 10 10" refX="9" refY="5" markerWidth="7" markerHeight="7" orient="auto-start-reverse"><path class="ah hi" d="M0,1 L9,5 L0,9 z"/></marker></defs><path class="e" d="M59,40 L173.8,40" marker-end="url(#ah14)"/><path class="e" d="M213.8,40 L328.6,40" marker-end="url(#ah14)"/><path class="e" d="M368.6,40 L483.4,40" marker-end="url(#ah14)"/><circle class="n" cx="40" cy="40" r="18"/><text class="t" x="40" y="40" dy=".35em" text-anchor="middle">Prd</text><circle class="n" cx="194.8" cy="40" r="18"/><text class="t" x="194.8" y="40" dy=".35em" text-anchor="middle">Det</text><circle class="n" cx="349.6" cy="40" r="18"/><text class="t" x="349.6" y="40" dy=".35em" text-anchor="middle">Map</text><circle class="n" cx="504.4" cy="40" r="18"/><text class="t" x="504.4" y="40" dy=".35em" text-anchor="middle">Rsp</text></svg><figcaption style="font-size:.82em;opacity:.72;margin-top:.45rem">Disaster cycle: Prd prediction and early warning, Det detection, Map damage mapping, Rsp response and recovery</figcaption></figure>
Key points.
- Flood extent is mapped rapidly from SAR imagery, because radar sees through cloud and works at night, and water appears dark.
- Active fires and burnt area are found using thermal and SWIR bands with the burn index $NBR = \frac{NIR - SWIR}{NIR + SWIR}$.
- Before-and-after images with CNN change detection identify collapsed buildings, blocked roads and damaged bridges.
- Machine-learning models on rainfall, slope, soil and land cover give flood and landslide susceptibility maps for early warning.
- Drones and high-resolution satellites give fresh images within hours, which guide rescue routes and relief camps.
- After the event, damage maps support insurance claims, compensation and reconstruction planning.
Example. Before a fire NIR 0.45, SWIR 0.15 gives $NBR_{pre} = 0.30/0.60 = 0.50$; after it NIR 0.20, SWIR 0.35 gives $NBR_{post} = -0.15/0.55 = -0.27$. $dNBR = 0.50-(-0.27) = 0.77$, which indicates high burn severity. dNBR = 0.77.
Hazard and best data.
| Hazard | Best data | AI task |
|---|---|---|
| Flood | SAR, optical after cloud clears | Water segmentation |
| Forest fire | Thermal, SWIR bands | Hotspot detection, burn severity |
| Earthquake | High-resolution optical, InSAR | Building damage classification |
| Landslide | DEM, rainfall, optical change | Susceptibility mapping |
| Cyclone | Geostationary satellite images | Track and intensity prediction |
Answer frame. Open with the definition; draw the four-stage disaster cycle; develop flood, fire and damage mapping with the sensor used for each; give the dNBR example; close by stating that speed of mapping is the main gain from AI.
Pitfall. Optical images are useless under cloud during floods and cyclones, so always name SAR as the alternative.
Precision agriculture and crop monitoring
<span style="display:inline-block;padding:.16em .6em;border:1.5px solid currentColor;border-radius:999px;font-size:.68em;font-weight:700;letter-spacing:.06em;text-transform:uppercase;opacity:.75">Not asked since 2022</span>
Definition. <mark>Precision agriculture uses satellite and drone imagery with AI to manage each part of a field according to its actual crop condition, saving inputs and raising yield.</mark>
Key points.
- Vegetation health is measured by $NDVI = \frac{NIR - Red}{NIR + Red}$, because healthy leaves reflect strongly in NIR and absorb red light.
- Classifiers map crop type and sown area, using time series of spectral bands through the growing season.
- Regression, random forest or LSTM models on NDVI, weather and soil data forecast crop yield before harvest.
- Water shortage, nutrient deficiency, pests and disease show early in spectral bands, before the eye can see them.
- Variable-rate application of water, fertiliser and pesticide follows these maps, which cuts cost and pollution.
- Drones with multispectral cameras give centimetre-level maps for small farms, and satellites cover whole districts for insurance and policy.
Example. With NIR 0.50 and Red 0.08, $NDVI = (0.50-0.08)/(0.50+0.08) = 0.42/0.58 = 0.72$, which means dense, healthy vegetation. NDVI = 0.72.
NDVI reading guide.
| NDVI value | Meaning |
|---|---|
| Below 0 | Water, snow or cloud |
| 0 to 0.2 | Bare soil, rock, built-up |
| 0.2 to 0.5 | Sparse or stressed vegetation |
| 0.5 to 0.9 | Dense, healthy vegetation |
Workflow.
<figure class="ds-fig" style="margin:1.4rem 0;overflow-x:auto"><svg xmlns="http://www.w3.org/2000/svg" id="dsfig-u5-03" viewBox="0 0 544.4 80" width="544.4" height="80" role="img" aria-label="Crop monitoring: Sat satellite or drone image, NDV NDVI and bands, Mod AI model for crop type, stress and yield, Adv advice to the farmer"><style>#dsfig-u5-03 .e{stroke:#454C5A;stroke-width:1.4;fill:none}#dsfig-u5-03 .e.hi{stroke:#2340B8;stroke-width:2.6}#dsfig-u5-03 .n{fill:#FFFFFF;stroke:#16181D;stroke-width:1.4}#dsfig-u5-03 .n.hi{fill:#E3E9FC;stroke:#2340B8;stroke-width:2.2}#dsfig-u5-03 .n.rb-b{fill:#16181D;stroke:#16181D}#dsfig-u5-03 .n.rb-r{fill:#BD3227;stroke:#BD3227}#dsfig-u5-03 text{font-family:"JetBrains Mono",ui-monospace,Menlo,Consolas,monospace;font-size:13px}#dsfig-u5-03 .t{fill:#16181D;font-weight:500}#dsfig-u5-03 .t.inv{fill:#FFFFFF;font-weight:700}#dsfig-u5-03 .kd{stroke:#16181D;stroke-width:1.2}#dsfig-u5-03 .dot{fill:#16181D}#dsfig-u5-03 .ann{fill:#2340B8;font-size:11px;font-weight:700}#dsfig-u5-03 .lbl{fill:#6F7787;font-family:system-ui,-apple-system,sans-serif;font-size:12px;font-weight:700}#dsfig-u5-03 .ptr{fill:#2340B8;font-size:12px;font-weight:700}#dsfig-u5-03 .ah{fill:#454C5A}#dsfig-u5-03 .ah.hi{fill:#2340B8}#dsfig-u5-03 .wl rect{fill:#FFFFFF;stroke:#DCE0E7}#dsfig-u5-03 .wl .t{font-size:12px;font-weight:700}#dsfig-u5-03 .wl.hi rect{fill:#2340B8;stroke:#2340B8}#dsfig-u5-03 .wl.hi .t{fill:#FFFFFF}html.dark #dsfig-u5-03 .e{stroke:#B1B7C3}html.dark #dsfig-u5-03 .e.hi{stroke:#8FA3FF}html.dark #dsfig-u5-03 .n{fill:#161920;stroke:#E6E8ED}html.dark #dsfig-u5-03 .n.hi{fill:#1E2748;stroke:#8FA3FF}html.dark #dsfig-u5-03 .n.rb-b{fill:#E6E8ED;stroke:#E6E8ED}html.dark #dsfig-u5-03 .n.rb-r{fill:#FF7E71;stroke:#FF7E71}html.dark #dsfig-u5-03 .t{fill:#E6E8ED}html.dark #dsfig-u5-03 .t.inv{fill:#0F1115}html.dark #dsfig-u5-03 .kd{stroke:#E6E8ED}html.dark #dsfig-u5-03 .dot{fill:#E6E8ED}html.dark #dsfig-u5-03 .ann{fill:#8FA3FF}html.dark #dsfig-u5-03 .lbl{fill:#858D9C}html.dark #dsfig-u5-03 .ptr{fill:#8FA3FF}html.dark #dsfig-u5-03 .ah{fill:#B1B7C3}html.dark #dsfig-u5-03 .ah.hi{fill:#8FA3FF}html.dark #dsfig-u5-03 .wl rect{fill:#161920;stroke:#2A2E37}html.dark #dsfig-u5-03 .wl.hi rect{fill:#8FA3FF;stroke:#8FA3FF}html.dark #dsfig-u5-03 .wl.hi .t{fill:#0F1115}</style><defs><marker id="ah15" viewBox="0 0 10 10" refX="9" refY="5" markerWidth="7" markerHeight="7" orient="auto-start-reverse"><path class="ah" d="M0,1 L9,5 L0,9 z"/></marker><marker id="ahh15" viewBox="0 0 10 10" refX="9" refY="5" markerWidth="7" markerHeight="7" orient="auto-start-reverse"><path class="ah hi" d="M0,1 L9,5 L0,9 z"/></marker></defs><path class="e" d="M59,40 L173.8,40" marker-end="url(#ah15)"/><path class="e" d="M213.8,40 L328.6,40" marker-end="url(#ah15)"/><path class="e" d="M368.6,40 L483.4,40" marker-end="url(#ah15)"/><circle class="n" cx="40" cy="40" r="18"/><text class="t" x="40" y="40" dy=".35em" text-anchor="middle">Sat</text><circle class="n" cx="194.8" cy="40" r="18"/><text class="t" x="194.8" y="40" dy=".35em" text-anchor="middle">NDV</text><circle class="n" cx="349.6" cy="40" r="18"/><text class="t" x="349.6" y="40" dy=".35em" text-anchor="middle">Mod</text><circle class="n" cx="504.4" cy="40" r="18"/><text class="t" x="504.4" y="40" dy=".35em" text-anchor="middle">Adv</text></svg><figcaption style="font-size:.82em;opacity:.72;margin-top:.45rem">Crop monitoring: Sat satellite or drone image, NDV NDVI and bands, Mod AI model for crop type, stress and yield, Adv advice to the farmer</figcaption></figure>
Answer frame. Open with the definition of precision agriculture; draw the workflow above; develop NDVI, crop mapping, yield forecast, stress detection and variable-rate application in that order; give the NDVI example; close with saving of inputs and higher yield.
Last-minute revision
- Land cover is what covers the ground; land use is what people do with it.
- LULC accuracy is checked with a confusion matrix, overall accuracy and kappa.
- Kappa = (p_o - p_e)/(1 - p_e); the example gives 0.70.
- NDVI = (NIR - Red)/(NIR + Red); healthy vegetation is high, about 0.6 to 0.9.
- NDWI = (Green - NIR)/(Green + NIR) is positive over open water.
- NBR = (NIR - SWIR)/(NIR + SWIR) maps burnt area; dNBR is pre minus post.
- SAR is preferred for floods because it penetrates cloud and works at night.
- Damage assessment compares before and after images with CNN change detection.
- Precision agriculture means variable-rate inputs guided by crop condition maps.
- Yield forecasting uses NDVI time series with weather data in regression or LSTM models.
Memory hooks
- LULC: cover is what you see, use is why it is there.
- NDVI is New minus Red over New plus Red, where New means NIR.
- Floods need radar (SAR), fires need SWIR, crops need NIR.
- Disaster cycle: predict, detect, map, respond.
- Kappa removes luck: observed minus chance, over one minus chance.
Coverage checklist
- Land cover and land use mapping: definition, workflow, classifiers, accuracy, kappa example; no past questions in the supplied papers.
- Environmental monitoring and assessment: water, forest, air, thermal, NDWI example; no past questions in the supplied papers.
- Disaster management and response: floods, fire, damage, susceptibility, dNBR example; no past questions in the supplied papers.
- Precision agriculture and crop monitoring: NDVI, crop type, yield, stress, variable rate; no past questions in the supplied papers.