Open navigation

Analytics description and requirements

 

Analytics

Definition / Deliverables

Delivery time

Requirements

Operating requirements

 Required inputs

Output

Format

Basic Maps Package



Set of tools for a visual analysis and mapping of fields with collaborative annotation and delineation capacities.


Orthophoto with reflectance maps for multispectral sensor and DSM and Scouting maps:


Bird View (RGB)


Crop Vigor (NDVI): Map to analyse vigor, that is mix of biomass development and crop health. The basic tool to scout for field anomalies.


Green Biomass (MCARI2): Map that is a good predictor of green leaf area index to analyse biomass development.

Greenness (VARI): Map to discriminate green plants from the remaining, soil as an example.


Chlorophyll content (NDRE), Map to analyse chlorophyll content, thanks to an index that correlates well with chlorophyll. The basic tool for nitrogen recommendation based on chlorophyll analysis


Photochemical Reflectance Index (PRI): Map that values spectral bands where photosynthetic pigments might be affected by water stress conditions such as chlorophyll and carotenoids.


GCP can be added and pointed.

1 business day

List of compatible multispectral sensors: Micasense Redege 3, mini, MX and Dual, M4C, Sequoia, PRI + RGB sensors 

Min 80% of sidelap and front overlap for fixed wing  and multirotor. 


Lack of overlap will have impact on the quality of the orthophoto and will prevent running some analytics

See below the required bands so that the analytics is delivered:


Bird View (RGB): Red, Blue and green bands or RGB sensor

Crop Vigor (NDVI): Red and NIR bands

Green Biomass (MCARI2),

Greenness (VARI):  RGB sensor

Chlorophyll content (NDRE): Red and red Edge bands


PRI: R570 and R531


Calibration target pictures


GCP if any

.tif

Advanced Scouting Maps

Chlorophyll concentration (CCCI): Map that is correlated to N Status / Chlorophyll concentration and can be valued to benchmark chlorophyll status or feed nitrogen variable rate maps


Colored Infrared (CIR): false color photograph that highlights vegetation


Soil Adjusted Crop Vigor (MSAVI2): Map to analyse crop vigor, that is mix of biomass development and crop health to scout for field anomalies. Main difference with NDVI is that it removes partly the effect of soils. Thus, this index is more suitable to use at early stage of crop development or where canopy is not closed. This is an MSAVI2 map, that is a combination of red and NIR infrared

1 business day


List of compatible multispectral sensors: Micasense Redege 3, mini, MX and Dual, M4C, Sequoia


Min 80% of sidelap and front overlap for fixed wing  and multirotor. 


Lack of overlap will have impact on the quality of the orthophoto and will prevent running some analytics


See below the required bands so that the analytics is delivered

CCCI: Red, Red Edge and NIR bands


CIR: NIR, Red and Green bands


MSAVI2: NIR and Red bands


Basic package should have been processed


.tif
Custom composition map

Composition map (orthomosaic) based on 3 predefined bands



1 business day
List of compatible multispectral sensors: Micasense Redege 3, mini, MX and Dual, M4C, Sequoia

Min 80% of sidelap and front overlap for fixed wing  and multirotor. 


Lack of overlap will have impact on the quality of the orthophoto and will prevent running some analytics


Reflectance map processed in Delair.ai or from an external software


.tif
Custom Scouting map

Custom Scouting map (or vegetation indice) based on calculation from predefined band
1 business day
Reflectance map processed in Delair.ai or from an external software
Microplot Vectorization

Digitalize and georeference microplot boundaries: delineate microplots boundaries to then measure, benchmark and monitor traits of varieties  / trial responses at microplot level. Microplot customer id is linked to each microplot to enable seamless data analysis. The reference file for trait / trial responses data storage.


Deliverables:

- parent_id: block or field Id 

- block_id: customer -block or field name

- block_row_id: customer -row id of the microplot, within a block or a field 

- block_col_id: customer column id of the microplot, within a block or a field 

- block_plot_id: customer id of the microplot


5 business days

List of compatible sensors: 

Multispectral: 

Micasense Redege 3, mini, MX and Dual, M4C, Sequoia and RGB sensors (no rolling shutter)


All the microplots must have the same design



Basic package

Experimental design (excel file): breakdown of the trial

Block_row_id: customer row id of the microplot, within a block or a field 

Block_col_id: customer column id of the microplot, within a block or a field 

block_plot_id:  customer id of the microplot

block_id: customer block or field name (optional)

Number of row per microplots

Number of row of analysis

Plant and row spacing

Row length

Alley  size

Field trial boundaries

Start of the field trial

(see details here)


.geojson

.shp



Microplot boundaries adjustment

Adjust the position of an existing microplot vector processed within Delair.ai (from another flight for example) or with an external software.


Deliverables:

- Adjusted Microplot vector file


5 business days

Basic package

Microplot vector file in geojson or shp format

Experimental design (optional)


.geojson

.shp*


Row Vectorization

Detect, digitize and measure rows within fields: for guidance of machine for example


Deliverables : 

Rows digitization with the following attributes:

- row id

- parent id (microplots) and vegetation length in case of microplots


3 business days
List of compatible multispectral sensors: Micasense Redege 3, mini, MX and Dual, M4C, Sequoia, + RGB sensors 

Available for crops planted in row and where bare soil is visible in between the rows


Basic package

Boundaries of the field or microplots

Row spacing


.geojson

.shp*


Statistics by plots

Extract statistics metrics of scouting maps at the microplots level.


Deliverables: 

Statistics/Microplots for each selected scouting maps with the following attributes:

min, max, average, standard deviation, variance


1 business days
Quantitative scouting maps - CIR and RGB out of scope

Basic package, Microplots boundaries


.geojson

.shp*

.csv


Bare soil model estimation

Estimate terrain elevation (DTM) in field with vegetation


3 business day


Compatible multispectral sensors: Micasense Redege 3, mini, MX and Dual, M4C, Sequoia, + RGB sensors 


Areas of bare soil must be visible in the survey (such as alleys or tracks) in order to estimate the DTM


Basic package

DSM

Field boundaries or Microplot boundaries


.tif
Plant Height

Estimate plant height for phenotyping or volume estimation in forestry


Deliverables: 

Vegetation height map

Statistics at field / microplots level:

  • Max

  • Min

  • Mean

  • Std-dev

  • Var

  • Pix-nb: number of pixel in the microplot


3 business days


Plants should be taller than 50 cm,

Overlap and sidelap of min 80%


DSM from an existing survey with bare soil (=DTM)

Or

Estimated DTM from Bare soil model estimation analytic (see above)


DSM of the flight with vegetation you want to measure


Boundaries of the field or microplot boundaries


Vegetation Height Map: 

.tif


Stats:

.geojson

.shp*

.csv


Gaps & Count

Detect and count plants and gaps 


Deliverables (in geojson and csv format):

“Gaps” output- only for plants in rows with the following attributes: 

- gap id

- gap length

- position of gaps at line end or not

“Plant count” output with the following attributes per microplot or field:

- Number of plant

- Length: sum of row length

- Gaps: sum of gap length

- row_count: number of rows

- plant_length: vegetation length

- canopy_radius: average plant canopy radius

- veg_ratio: total vegetation length/sum of row length

- row_anomaly: indicates if anomaly within the rows

- anomaly: indicates if anomaly within plant count

“Rows with plant count” output with the following attributes per rows:

- Length: row length

- Plant count per row

- Gaps: sum of gap length per row

- Row id

- Plant_lenght: vegetation length per row

- Veg_ratio: vegetation length / row length

- Row anomaly: indicates if anomaly within the row

- Canopy radius: average plant canopy radius per row


1 business days

List of compatible multispectral sensors: Micasense Redege 3, mini, MX and Dual, M4C, Sequoia, RGB sensors 


It is mandatory to see bare ground in between two plants on the map, or only visible gaps will be detected. 

For row crops, with 6cm of GSD and a multispectral camera, optimal corn stage will be 4 leaves, and starbud for sunflower. With enhanced resolution, earlier stages can be targeted. The basic rule is : size of GSD <= half canopy size (ie: plant width seen from above) 


For orchard / vineyard: plant must be planted in row. if canopy is closed, only gaps will be detected. Height of the plant must be > 50cm

For palm trees, plant must be > 50 cm


Basic package


Boundaries of the field or microplots


Rows spacing for production field and orchard / vineyard planted in rows


Inter plant spacing


For Gaps, Plant Count and Rows outputs:


.geojson

.shp*

.csv


Flowering Characterization

Estimate % of flowering for row crops - canola and sunflower

Deliverables:

Flowering mask 

Flowering % per microplot


1 business days
List of compatible multispectral sensors: Micasense Redege 3, mini, MX and Dual, M4C, Sequoia, + RGB sensors 
Yellow flowers visible from the sky

Basic package (bird view / RGB)

Boundaries of the field or microplots


Mask: .tif

Flowering%:

.geojson

.shp*

.csv


Emergence Characterization

Estimate % of green at early stage of crops to characterise seedling vigor

Deliverables:

Emergence mask 

Emergence % per microplot


1 business days
Available for crops planted in row and where bare soil is visible in between the rows

Basic package

Gaps and count

Boundaries of the field or microplots


Mask: .tif

Emergence%:

.geojson

.shp*

.csv


Stay Green

A measure of a crop ability to stay as a green growing plant in late-season plant

Deliverables:

Stay green mask

Stay green % per microplot


1 business days
RGB is prefered

Basic package

Boundaries of the field or microplots


Mask: .tif

Staygreen%:

.geojson

.shp*

.csv


FCOVER

A measure of the fraction of ground covered by green vegetation. Practically, it quantifies the spatial extent of the vegetation

Deliverables:

Biomass mask 

Fcover per microplot


1 business days

Basic package

Boundaries of the field or microplots


Mask: .tif

FCOVER%:

.geojson

.shp*

.csv


Weed management

Detects weeds on bare soil or row crops and generates a prescription map

Deliverables:

Prescription map that can be exported to a sprayer


3 business days
Micasense RedEdge 3, mini, and MX
GSD max: 5 cm

Basic package

Boundaries of the field (category : Field boundaries)

Rows for row crops 


.shp

.geojson


*On demand only


Did you find it helpful? Yes No

Send feedback
Sorry we couldn't be helpful. Help us improve this article with your feedback.