All configuration parameters

Name	Default Value	Description	Type	Name
a_crop_label_replacement	[‘10’, ‘annual_crop’]	Replace a label by a string	list	a_crop_label_replacement
acor_feat	False	Apply atmospherically corrected features	bool	acor_feat
additional_features		OTB’s bandmath expressions, separated by comma	str	additional_features
allowed_retry	0	Allow dask to retry a failed job N times.	int	allowed_retry
angle	True	If True, smoothing corners of pixels (45°)	bool	angle
annual_classes_extraction_source	None		str	annual_classes_extraction_source
annual_crop	[‘11’, ‘12’]	The list of classes to be replaced by previous data	list	annual_crop
arbo	/*	The input folder hierarchy	str	arbo
auto_date	True	Enable the use of start_date and end_date	bool	auto_date
autocontext_iterations	3	Number of iterations in auto-context.	int	autocontext_iterations
band_ref	1	Number of the band of the VHR image to use for coregistration	int	band_ref
band_src	3	Number of the band of the src raster to use for coregistration	int	band_src
bingdal	None	path to GDAL binaries	str	bingdal
blocksize	2000	block size to split raster to prevent Numpy memory error	int	blocksize
buffer_size	None	Define the working size batch in number of pixels	int	buffer_size
builders_class_name	[‘i2_classification’]	The name of the class defining the builder	list	builders_class_name
builders_paths	/path/to/iota2/sources	The path to user builders	list	builders_paths
check_inputs	True	Enable the inputs verification.	bool	check_inputs
chunk	10	Number of chunks for statistics computing	int	chunk
chunk_size_mode	split_number	The chunk split mode, choices are ‘split_number’ or ‘user_fixed’	str	chunk_size_mode
chunk_size_x	50	The number if rows for chunk	int	chunk_size_x
chunk_size_y	50	The number if rows for chunk	int	chunk_size_y
classif_mode	separate	‘separate’ or ‘fusion’.	str	classif_mode
classification	None	Input raster of classification	str	classification
classifier	None	Choose the classification algorithm	str	classifier
clipfield	None	field to identify distinct areas	str	clipfield
clipfile	None	vector-based file to clip output vector-based classification	str	clipfile
clipvalue	None	value of field which identify distinct areas	int	clipvalue
cloud_threshold	0	Threshold to consider that a pixel is valid	int	cloud_threshold
color_table	None	Absolute path to the file which link classes and their colors	str	color_table
concat_mode	True	Enable the use of all features	bool	concat_mode
confidence	None	Input raster of confidence	str	confidence
copy_input	True	use spectral bands as features	bool	copy_input
crop_mix	False	Enable crop mix option	bool	crop_mix
cross_validation_folds	5	The number of k-folds	int	cross_validation_folds
cross_validation_grouped	False		bool	cross_validation_grouped
cross_validation_parameters	{}		dict	cross_validation_parameters
data_field	None	Field name indicating classes labels in ground_thruth	str	data_field
data_mode_access	gapfilled	Choose which data can be accessed in custom features	str	data_mode_access
date_src	None	Date YYYYMMDD of the reference image	str	date_src
date_vhr	None	Date YYYYMMDD of the VHR image	str	date_vhr
deep_learning_parameters	{}	deep learning parameter description is available here	dict	deep_learning_parameters
dempster_shafer_sar_opt_fusion	False	Enable the use of both SAR and optical data to train a model.	bool	dempster_shafer_sar_opt_fusion
dempstershafer_mob	precision	Choose the dempster shafer mass of belief estimation method	str	dempstershafer_mob
dim_red	False	Enable the dimensionality reduction mode	bool	dim_red
douglas	10	Douglas-Peucker tolerance for vector-based generalization	int	douglas
dozip	True	Zip output vector-based classification (OSO-like production)	bool	dozip
enable_autocontext	False	Enable the auto-context processing	bool	enable_autocontext
enable_probability_map	False	Produce the probability map	bool	enable_probability_map
end_date		The end date of interpolated image time series	str	end_date
exogeneous_data	None	Path to a Geotiff file containing additional data to be used in external features.	str	exogeneous_data
external_features_flag	False	Enable the external features mode	bool	external_features_flag
extract_bands	False		bool	extract_bands
features	[‘NDVI’, ‘NDWI’, ‘Brightness’]	List of additional features computed	list	features
features_from_raw_dates	False	learn model from raw sensor’s date (no interpolations)	bool	features_from_raw_dates
fill_missing_dates	False	Fill raw data with no data if dates are missing	bool	fill_missing_dates
first_step	None	The step group name indicating where the chain start	str	first_step
force_standard_labels	False	Standardize labels for feature extraction	bool	force_standard_labels
full_learn_segment	False	Enable the use of entire segment for learning	bool	full_learn_segment
functions	None	The function list to be used to compute features.Can be a string of space-separated function namesCan be a list of either strings of function nameor lists of one function name and one argument mapping	list	functions
fusion_options	-nodatalabel 0 -method majorityvoting	OTB FusionOfClassification options for voting method involved if classif_mode is set to ‘fusion’	str	fusion_options
fusionofclassification_all_samples_validation	False	Enable the use of all reference data	bool	fusionofclassification_all_samples_validation
grasslib	None	path to grasslib	str	grasslib
gridsize	None	Number of lines and columns of serialization process	int	gridsize
ground_truth	None	Absolute path to reference data	str	ground_truth
hermite	10	Hermite Interpolation threshold for vector-based smoothing	int	hermite
higher_stats	False	If True, compute more complexe statistics (Shanon, majority order and difference, etc.)	bool	higher_stats
inland	None	Inland water limit shapefile	str	inland
iterate	True	Proceed several iteration by reducing the step between geobin to find SIFT points	bool	iterate
keep_bands	[‘B1’, ‘B2’, ‘B3’, ‘B4’, ‘B5’, ‘B6’]	The list of spectral bands used for classification	list	keep_bands
keep_duplicates	True	use ‘rel_refl’ can generate duplicated feature (ie: NDVI), set to False remove these duplicated features	bool	keep_duplicates
keep_runs_results	True		bool	keep_runs_results
l5_path_old	None	Absolute path to Landsat-5 images coming from old THEIA format (D*H*)	str	l5_path_old
l8_path	None	Absolute path to Landsat-8 images comingfrom new tiled THEIA data	str	l8_path
l8_path_old	None	Absolute path to Landsat-8 images coming from old THEIA format (D*H*)	str	l8_path_old
last_step	None	The step group name indicating where the chain ends	str	last_step
lcfield	Class	Name of the field to store landcover class in vector-based classification	str	lcfield
lib64bit	None	Path of BandMath and Concatenate OTB executables returning 64-bits float pixel values	str	lib64bit
list_tile	None	List of tile to process, separated by space	str	list_tile
logger_level	INFO	Set the logger level: NOTSET, DEBUG, INFO, WARNING, ERROR, CRITICAL	str	logger_level
max_nn_inference_size	None	maximum batch inference size	int	max_nn_inference_size
maximum_cpu	4	The maximum number of CPU available	int	maximum_cpu
maximum_ram	16	The maximum amount of RAM available. (gB)	int	maximum_ram
merge_final_classifications	False	Enable the fusion of classifications mode, merging all run in a unique result.	bool	merge_final_classifications
merge_final_classifications_method	majorityvoting	Indicate the fusion of classification method: ‘majorityvoting’ or ‘dempstershafer’	str	merge_final_classifications_method
merge_final_classifications_ratio	0.1	Percentage of samples to use in order to evaluate the fusion raster	float	merge_final_classifications_ratio
merge_final_classifications_undecidedlabel	255	Indicate the label for undecision case during fusion	int	merge_final_classifications_undecidedlabel
minimum_required_dates	2	required minimum number of available dates for each sensor	int	minimum_required_dates
minsiftpoints	40	Minimal number of SIFT points to find to create the new RPC model	int	minsiftpoints
minstep	16	Minimal size of steps between bins in pixels	int	minstep
mmu	1000	MMU of output vector-based classification (projection unit),(Default : 0.1 ha)	int	mmu
mode	2	Coregistration mode of the time series	int	mode
mode_outside_regionsplit	0.1	Fix the threshold for split huge model	float	mode_outside_regionsplit
model_type	None	machine learning algorthm’s name	str	model_type
module	/path/to/iota2/sources	Absolute path for user source code	str	module
no_data_value	-10000	value considered as no_data in features map mosaic (i2_features_map builder name)	int	no_data_value
no_label_management	maxConfidence	Method for choosing a label in case of fusion	str	no_label_management
nomenclature	None	configuration file which describe nomenclature	str	nomenclature
nomenclature_path	None	Absolute path to the nomenclature description file	str	nomenclature_path
number_of_chunks	50	The expected number of chunks	int	number_of_chunks
obia_segmentation_path	None	Filename for input segmentation	str	obia_segmentation_path
otb_classifier_options	None	OTB option for classifier. If None, the OTB default values are used.	dict	otb_classifier_options
outprefix	dept	Prefix to use for naming of vector-based classifications	str	outprefix
output_name	None	Temporary chunks are written using this name as prefix	str	output_name
output_path	None	Absolute path to the output directory.	str	output_path
output_prev_features	None	Path to previous features for crop mix	str	output_prev_features
output_statistics	False	Enable the writing of PNG files containing additional statistics	bool	output_statistics
padding_size_x	0	The padding for chunk	int	padding_size_x
padding_size_y	0	The padding for chunk	int	padding_size_y
pattern	None	Pattern of the time series files to coregister	str	pattern
patterns	ALT,ASP,SLP	key name for detect the input images	str	patterns
prec	3	Estimated shift between source and reference raster in pixel (source raster resolution)	int	prec
prev_features	None	Path to a configuration file used to produce previous features	str	prev_features
prod	None	OSO-like output vector (aliases) is produced. Other possible value : carhab	str	prod
proj	EPSG:2154	The projection wanted. Format EPSG:XXXX is mandatory	str	proj
random_seed	None	Fix the random seed for random split of reference data	int	random_seed
ratio	0.5	Should be between 0.0 and 1.0 and represent the proportion of the dataset to include in the train split.	float	ratio
reduction_mode	global	The reduction mode	str	reduction_mode
region_field	region	The column name for region indicator in`region_path` file	str	region_field
region_path	None	Absolute path to region vector file	str	region_path
region_priority	None	Define a order for region intersection	list	region_priority
rel_refl	False	Compute relative reflectances by the red band	bool	rel_refl
remove_output_path	True	Enable the removing of complete output_path directory	bool	remove_output_path
resample	True	Resample the reference and the source rasterto the same resolution to find SIFT points	bool	resample
rssize	20	Resampling size of input classification raster (projection unit)	int	rssize
runs	1	Number of independant runs processed.	int	runs
s1_path	None	Absolute path to Sentinel-1 configuration file	str	s1_path
s2_l3a_output_path	None	Absolute path to store preprocessed data in a dedicated directory.	str	s2_l3a_output_path
s2_l3a_path	None	Absolute path to Sentinel-2 L3A images (THEIA format)	str	s2_l3a_path
s2_output_path	None	Absolute path to store preprocessed data in a dedicated directory.	str	s2_output_path
s2_path	None	Absolute path to Sentinel-2 images (THEIA format)	str	s2_path
s2_s2c_output_path	None	Absolute path to store preprocessed data in a dedicated directory.	str	s2_s2c_output_path
s2_s2c_path	None	Absolute path to Sentinel-2 images (Sen2Cor format)	str	s2_s2c_path
sample_augmentation	{‘activate’: False}	OTB parameters for sample augmentation	dict	sample_augmentation
sample_management	None	Absolute path to a CSV file containing samples transfert strategies	str	sample_management
sample_selection	{‘sampler’: ‘random’, ‘strategy’: ‘all’}	OTB parameters for sample selection	dict	sample_selection
sample_validation	{‘sampler’: ‘random’, ‘strategy’: ‘all’}	OTB parameters for sampling the validation set	dict	sample_validation
samples_classif_mix	False	Enable the second step of crop mix	bool	samples_classif_mix
sampling_validation	False	Enable sampling validation	bool	sampling_validation
seed	1	Seed of input raster classification	int	seed
spatial_resolution	10	Output spatial resolution	list	spatial_resolution
split_ground_truth	True	Enable the split of reference data	bool	split_ground_truth
standardization	False		bool	standardization
start_date		The first date of interpolated image time series	str	start_date
stats_used	[‘mean’]	List of stats used for train and classification	list	stats_used
statslist	{1: ‘rate’, 2: ‘statsmaj’, 3: ‘statsmaj’}	dictionnary of requested landcover statistics	dict	statslist
step	256	Initial size of steps between bins in pixels	int	step
systemcall	False	If True, use yours gdal lib (cf. bingdal)	bool	systemcall
target_dimension	4	The number of dimension required, according to reduction_mode	int	target_dimension
temporal_resolution	16	The temporal gap between two interpolation	int	temporal_resolution
umc1	None	MMU for first regularization	int	umc1
umc2	None	MMU for second regularization	int	umc2
use_additional_features	False	Enable the use of additional features	bool	use_additional_features
use_gapfilling	True	Enable the use of gapfilling	bool	use_gapfilling
user_feat_path	None	Absolute path to the user’s features path	str	user_feat_path
validity	None	Input raster of validity	str	validity
validity_threshold	1		int	validity_threshold
vectorize_fusion_of_classifications	False	flag to inform iota2 to vectorize the fusion of classifications	bool	vectorize_fusion_of_classifications
vhr_path	None	Absolute path to VHR path	str	vhr_path
write_outputs	False	Write temporary files	bool	write_outputs
write_reproject_resampled_input_dates_stack	True	Enable the write of resampled stack image for each date	bool	write_reproject_resampled_input_dates_stack
zonal_vector	None	vector file to compute zonal statistics of classification	str	zonal_vector