Questions tagged [machine-learning]
Field of study that gives computers the ability to learn without being explicitly programmed
78
questions
-1
votes
0answers
42 views
Roof color recognition
I have experience in GIS and data analysis. I am doing an internship and I've been asked to classify the colors of the rooftops of a city (in this case, Vienna)
I have all the Vienna buildings ...
0
votes
0answers
48 views
Adding point features by machine learning in QGIS 3.16
I've got several georeferenced traditional maps and there are circles on it. (these are the studied points) So I want to add point features to the middle of the circles. I could do it manually, but I ...
3
votes
0answers
33 views
Extract values from rasterstack TIFF for point data locations in Python
I am working on machine learning algorithms for predicting wildfire sites on state level. I have a CSV of wildfire instances, that has 37 columns including a geometry column, a lat column and a lon ...
2
votes
0answers
38 views
How to programmatically identify landmarks (cemeteries) in Google Maps satellite data?
I'm searching Google Maps satellite view for cemeteries that are not listed in common repositories of cemeteries. I've spent a lot of time cruising around satellite mode searching for small ...
1
vote
1answer
68 views
Extracting only part of supervised output model in Raster format
I have a svm predicted model which when applied on raster images classifies the LULC of land and writes the output to raster file. I want to use only the Land used part out of the output raster image. ...
0
votes
0answers
32 views
Extracting a part of SVM predicted output
I have predicted few raster images using svm model. I'm trying to mask only part of predicted model to a raster file . Classification is arrayof 1's and 2's which represents land use and land cover. ...
0
votes
0answers
28 views
Prediction of Sentinel images by SVM classifier
I'm looking for a way to reduce the time taken by SVM classifier (without changing the dimenisons of my training data or data on which prediction has to be done) to predict the raster image data.
I ...
2
votes
2answers
45 views
How were walkways found and added to Google Maps or OSM?
Does Google Maps or OSM use any deep learning or machine learning model to extract walkways from satellite images? Examples of walkways are the green lines in the picture here. I wonder how they were ...
1
vote
0answers
30 views
Preparing training data for crop species classification from drone images
I have high resolution multispectral (R,G,B,NIR,RE bands) images of a field taken from MicaSense RedEdge mounted on a drone. There are various species of crops planted. I want to classify the crops or ...
3
votes
4answers
264 views
Performing supervised classification on Sentinel images
I'm looking for python code which predicts the LULC of my data(other raster files apart from refernce data band1, band2 and soon) using svm classifier with rbf kernel based on reference data (truth ...
0
votes
0answers
20 views
Combining classified data from QGIS with respective map from Google Earth Engine
I imported from GEE into QGIS a Sentinel 2 map, I used QGIS to classify it in a new layer, I then extracted he classification layer as a .tif file. How do I combine the classified data with the map ...
0
votes
1answer
76 views
Google Earth Engine: get data ready for ML export
I need to export data from GEE to get processed in MATLAB. I want to export CSV files of a region, aggregating meteo data ( CAMS, ERA5, MODIS AOT) with sentinel-2 images. These images have already ...
0
votes
0answers
19 views
Where to find open tabular hyperspectral data for machine learning research?
Where can i find open datasets regarding " Wheat/Maize Leaf Spectra with Associated water content, Potassium and Nitrogen Measurements" for machine learning research i.e. hyperspectral ...
0
votes
1answer
34 views
Same confusion matrix depiste hyperparameter tuning using TrainImageClassifier in OTB
I am trying to run a land use land cover classification using TrainImageClassifier in OTB. Here are the settings I used :
The problem is that no matter how much I tweak the hyperparameters of any of ...
0
votes
0answers
49 views
Classified image using RF method in R displays less no. of classes than it was trained to
I am trying to classify crops using Sentinel-2 image including 10 classes, using randomForest classification in R. For that, I extracted 2000 random samples points from the training areas for 11 bands ...
1
vote
1answer
261 views
SMILE classifiers/regressors in Earth Engine
I am working on a project intended for publication that leans heavily on Earth Engine for much of the workflow: assembling, compositing, and mosaicking lots of images from multiple data sources, ...
-1
votes
1answer
58 views
Eliminating end points automatically
In QGIS 3.10 I have a point file and I decided a colors palettes for it.
Let's say this palette is composed by 11 colours steps, from blue to red and its intermediates.
So, I would like to ...
1
vote
0answers
19 views
Are there Sentinel crop labeled datasets available?
I am starting a project where I am going to use Sentinel-2 imagery and machine learning for detecting sugarcane and coffee. In order to train the algorithm I would need labeled sentinel datasets. I've ...
0
votes
0answers
38 views
Highly Imbalanced dataset
I have a dataset (vector data) that contains the polygons and their corresponding crop type. This data is highly imbalanced i.e, I have a lot of classes that contain one sample only, as shown in the ...
0
votes
0answers
13 views
Creating and Labeling time series (features)
I am trying to carry out crop type identification using optical remotely sensed data of Sentinel-2A. I am new to both fields (remote sensing and machine learning) and I want to use time series (NDVI, ...
0
votes
0answers
36 views
Spike and crater detection in DSM using machine learning / deep learning / computer vision techniques
I'd like to try machine learning / computer vision / deep learning approaches for detecting artifacts in Digital Surface Models, and am specifically interested in doing this for common artifacts like ...
1
vote
0answers
22 views
Ground Truth Data for India [closed]
I'm starting to get involved in a humanitarian project to understand crop-type and crop-yield in India to identify areas where they may be food shortages.
The current approach for this project is to ...
0
votes
0answers
23 views
How to relate flood events (points) with flood conditioning rasters for Machine Learning?
I have point shapefile of flood events which has either flood occur or not.
On the other hand, I have 13 flood conditioning rasters i.e. slope, elevation, rainfall etc. these are all at 30 meter ...
2
votes
1answer
361 views
Google Earth Engine: Evaluate classifier of output type regression
Background
According to the Google Earth Engine documentation for supervised classification, the accuracy assessment of classifiers such as ee.Classifier.smileRandomForest can be done using a ...
2
votes
1answer
56 views
Predicting the whole image through trained classifier and visualize it as classified landuse and landcover image(LULC)
I am working on LULC classification of sentinel-2 image(4-bands) using Machine Learning algorithms. I split the whole image into 64*64 patches and assigned class label (builtup, barren land, water and ...
0
votes
0answers
19 views
RAM Problem When Loading HDF Datasets
I am trying to store my labels and features datasets extracted from 324 patches in an HDF file because loading them (labels and features) directly from the patches was failing since the RAM hits its ...
0
votes
1answer
88 views
Python code speed execution problem
I am trying to retrieve data from 324 eopatches I sampled beforehand. Patches are basically numpy arrays as explained in this documentation EOPatch.
This is an example of the content of a patch after ...
1
vote
0answers
57 views
KeyError: 'BANDS' and NameError: 'bands'
I am trying to follow this tutorial: land cover fastai
And while executing the workflow, I got this error:
eopatch 0 has been processed!
---------------------------------------------------------------...
0
votes
1answer
898 views
ValueError: too many values to unpack (expected 2)
I am trying to follow this tutorial: land cover fastai
And while executing the workflow, I got this error:
This is the code where the error occurs:
def png_gen(patch, inference=False):
"""Save ...
1
vote
2answers
319 views
Pre-trained transfer learning models for satellite image classification
I am currently working on a project that tackles crop type classification using machine learning and deep learning. Given the limited amount of satellite data that I have, transfer learning sounds ...
0
votes
0answers
36 views
Patch-based image classification!
To my knowledge, when building a CNN model for LULC classification of sat images using the pixel-based approach we consider each pixel as a training example and the number of input neurons equals the ...
1
vote
1answer
35 views
Using 3rd party PASCAL_VOC in arcgis.learn prepare_data() method
Has anyone had luck using the prepare_data method with data not exported from the Export Training Data tool in ArcGIS Pro? The documentation suggests prepare_data will take PASCAL_VOC_rectangles from ...
0
votes
0answers
105 views
ArcGIS Pro (2.3.0) Forest-based Classification and Regression Issue
I keep getting this error when I'm using the 'Predict to raster' Prediction Type in the Forest-based Classification and Regression tool:
'Problem extracting values from a.img using origin location [...
1
vote
1answer
274 views
Visualizing specific class from unsupervised classification in Earth Engine
I have classified an image into 20 classes using unsupervised classification for a specific region in Google Earth Engine. I want to check a specific class (say class 9) and visualize only that ...
3
votes
0answers
2k views
Encoding categorical variable for random forest with sklearn
I have a random forest model that works pretty well, taking a bunch of vanilla remote sensing raster data as input. I think it could be improved with addition of some information that I currently have ...
1
vote
0answers
39 views
Using computer vision for linear feature detection [closed]
I am considering to use CV methods to detect linear features in very high resolution imagery (i've added an example below). These linear features are made by animals which transverse this section of ...
5
votes
2answers
3k views
Earth Engine: Simplest way to move from EE image to array for use in sklearn?
I've produced a very large multiband image in EE with the goal of classifying it using the classifiers implemented in sklearn (the native ones implemented in EE don't provide enough flexibility for my ...
1
vote
3answers
1k views
Identify spatially contiguous clusters in raster data using kmeans
I would like to cluster the cells of a raster object into k contiguous regions using kmeans. The number of regions, k, is known. Each cell has various geographical attributes, such as temperature, ...
1
vote
0answers
28 views
Creating square grid polygons from shapefile using ArcGIS Desktop and machine learning to predict wildfires [closed]
I'm currently working on a data science project where I would like to predict the probability of a wildfire in Washington state for a given location using machine learning.
I have latitude/longitude ...
2
votes
1answer
74 views
Applying machine learning methods in orfeo toolbox into DEM raster
I would like to apply machine learning methods in orfeo toolbox to classify some landscape features such as shrub and coarse woody debris in woodland. I created DEM raster image from very dense ground ...
0
votes
1answer
102 views
Practical limitations of image classification of large rasters?
Been attempting (with no success so far) to implement the random forest classification in ArcMap on a reasonably large image. If I throw a raster with say 20-30 bands in it, works fine, just takes ...
0
votes
1answer
111 views
Satellite imagery for download
I'm new to GIS and I'd like to apply some machine learning techniques to decent-quality satellite data for making certain types of predictions. This would potentially be for commercial purposes.
I'm ...
1
vote
0answers
625 views
KeyError: “The name 'ImageTensor:0' refers to a Tensor which does not exist. The operation, 'ImageTensor', does not exist in the graph.”
I'm trying to use ArcGIS Pro 2.3 and this tutorial (https://medium.com/geoai/high-resolution-land-cover-mapping-using-deep-learning-7126fee571dd) to use the function "Classify Pixels Using Deep ...
2
votes
0answers
47 views
Top conferences and journals in GIS [closed]
I want to submit a paper for some research that I have done. What are the top conferences and journals in this field?
2
votes
0answers
31 views
Is there an existing solution for pattern recognition?
I've been looking at modeling potential avalanche hazard based on terrain characteristics. I have a vector layer showing historical avalanche paths and have raster layers for elevation, aspect, slope,...
5
votes
0answers
1k views
Running OTB Random Forest Classification
I am having trouble processing a satellite image using the RF (Random Forest) classification, that is a machine learning algorithm in the Orfeo Toolbox of QGis 2.18.1.
When I run the Tool, the ...
4
votes
1answer
840 views
Split GeoTIFF into multiple cells with Rasterio
I'd like to create training data for a machine learning pipeline. To do this I want to take a large raster and split it into multiple equal sized cells.
I have a very basic loop for generating the ...
3
votes
0answers
108 views
Reproducing Paper Results for Land Cover Mapping of Satellite Imagery?
I am interested in training a neural network to perform pixel-based classification for land cover mapping of satellite data. In order to learn more about this interesting field I am trying to ...
0
votes
1answer
469 views
How to convert masks generated by rasterio to channel last mask
The problem is about using rasterio to generate mask from GeoJSON file which contains geographic coordinates.
The function that I used is from:
from rasterio.tools.mask import mask
with rasterio....
1
vote
0answers
610 views
SVM classification in R
I have the following dataframe containing training data to be used in a SVM classification. The first column ID must be avoided and the column Class contains the response variable.
> training_S
...
