Questions tagged [machine-learning]
Field of study that gives computers the ability to learn without being explicitly programmed
102
questions
0
votes
0
answers
11
views
Classification function error in Google Earth Engine (GEE) Code [closed]
Error in Google Earth Engine (GEE) Code -
"trainedClassifier.predict is not a function"
I'm working on a classification project in Google Earth Engine (GEE) using a Random Forest classifier. ...
0
votes
0
answers
12
views
Performing image classification with both a classifier definition file and a segmented image in ArcGIS Pro
I am performing object-based classifications in ArcGIS Pro in the form of two separate rounds of classifications.
In the first round, I obtained a drone image and uploaded it to GIS, I manually ...
0
votes
1
answer
64
views
Extracting features from DEM using ArcGIS Pro deep learning
I was wondering if it's possible to use ArcGIS Pro Deep learning to extract features from elevation data?
I have a DEM with multiple levees that are used for flood defence.
Is there a way to train ...
0
votes
0
answers
53
views
TFRecord dataset from Google Earth Engine
I am trying to create a dataset of 7 bands from tfrecord files that I downloaded from google earth engine, am I doing this correctly:# Define the feature columns for parsing the TFRecord data. I am ...
1
vote
1
answer
36
views
No valid data training when doing a supervised classification using training data from a different year
I'm doing a supervised classification using training data from a 2023 Image to a 2022 Image. However, when doing the migration I got the error message "No valid training data were found" for ...
1
vote
0
answers
38
views
Looping or mapping a classifier to retrain it on different images in Google Earth Engine
Is it possible to create a classifier (e.g. CART/Random Forest) and train it on several different training images with unique sample points each using a loop or .map()?
I have successfully created a ...
0
votes
0
answers
116
views
GEE - random forest doesn't classify my whole image
I'm new to GEE and I'm trying to do a machine learning supervised classification using random forest. it turns out that I made a code taking different parts of other codes and it works well for small ...
0
votes
0
answers
82
views
Calculating RMSE of random forest classification in Earth Engine via Python API
I tried to transform the following JS code to Python to get the RMSE values of my classification.
My ported code is the following
sampleTraining = predictedTraining.select(['kat_sajat', 'predicted'])
...
0
votes
0
answers
29
views
Stack some classifier probabilities for calculate MinDist of them
As I mentioned in title I calculated, SVM, CART, RF for my dataset. Now I need to stack them all. For each pixel I have 5 classes, so at the end, there will be 15 probability for each pixel. Then With ...
1
vote
0
answers
71
views
How to apply GEE training data to a new region
The link to my code is included here but I will paste it as well: https://code.earthengine.google.com/c9b3aec923007e896a3a079446001dac
I am trying to dynamically classify ground cover using supervised ...
0
votes
0
answers
32
views
Feature Selection for Geospatial Vector Data Classification
The problem I am exploring right now is a binary classification problem about classifying road intersections into roundabouts or not roundabouts. The available input data consists of the GPS latitude /...
0
votes
2
answers
42
views
Using .sav Files in Geoprocessing Tools
Platform: ArcGIS Pro 3.0.4
Situation: I want to create a geoprocessing tool that uses a sklearn machine learning model (saved in .sav format). The goal is that users will be able to input a new table ...
0
votes
0
answers
28
views
Faster method to not consider NaN during RF classification?
To classify the pixels of a Sentinel-2 image I am using a Random Forest model.
Firstly, I am reading and stacking bands and indices pré-calculated from Sentinel-2 data (19 rasters in total with size ...
1
vote
1
answer
194
views
How to export decision trees from GradientTreeBoost in Google Earth Engine?
I'm running the Google Earth Engine examples for ee.Classifier.smileGradientTreeBoost and ee.Classifier.smileRandomForest, which are basically the same but with different training methods.
I was ...
0
votes
0
answers
50
views
Random forest and svm classification taking hours to run
I am performing crop classification using random forest technique on Sentinel-2 data. The file size of image on which classification has to be performed is only 26 mb.
I am using Jupyer notebook. Any ...
0
votes
0
answers
21
views
Max Ent enviromental layers for archaeology
First, I have to put you in context. I got trouble with some of my raster layers, I'm trying to apply max ent in archaeology. What I want to do is to predict the areas where are a higher probability ...
0
votes
1
answer
102
views
Raster to CSV or XYZ
I'm trying to apply spatial data mining to a set of vector and raster files so I need a way to convert my raster archives into a CSV in order to run the mining
A little bit of background, my thesis is ...
0
votes
1
answer
37
views
Should I re-scale all the dataset to one scale before running them into model?
I have been working on the Flood susceptibility modelling and also have identified, collected and generated data of around 26 controlling factors(indicators). Furthermore, i'm going to put them into ...
1
vote
1
answer
365
views
SVM Classifier Probability Output is Opposite of RF and CART Classifiers using Google Earth Engine
I am working on a Peatland Fire Fire Susceptibility Determination on GEE using three classifier algorithms: RF, CART, and SVM. The outputs are fire probability and binary classification (1 = fire, 0 = ...
1
vote
0
answers
86
views
Satellite image segmentation using transfer learning with input image of different size and channels
I am new to Deep Learning and recently developed land cover products using U-Net architecture. I have been using an open-source library called segmentation_model and it worked pretty well with a mean ...
0
votes
1
answer
117
views
I am trying to perform a machine learning analyis using the ArcGIS module in Jupyter notebooks but strange error
I was trying to import all modules for ArcGIS to perform a machine learning analysis. However, the code gives me an error at the line from arcgis.learn.
Code:
%matplotlib inline
import pandas as pd
...
2
votes
0
answers
83
views
Using images from different Landsat missions and Sentinel-2 for machine learning
I am doing some image segmentation using random forests on satellite imagery. The events I am trying to detect are somewhat rare so my training sets are very limited if I want to use Sentinel-2 ...
3
votes
0
answers
41
views
Projection best practices for applying ML to large scale Earth Observation imagery [closed]
I come from a data science background, rather than GIS, but work in a domain where remote-sensed imagery is widely used; so I'm still learning some of the do's & don'ts when it comes to the 'right'...
1
vote
1
answer
1k
views
Adding a column to a Google Earth Engine feature collection
I am trying to generate a ground truth feature collection to do some machine learning. I have a shapefile that contains one class of my ground truth. and I am manually creating a second feature ...
1
vote
0
answers
32
views
Reusing regression or machine learning model in subsequent years
I have collected high-resolution UAV imagery and leaf area index (LAI) plot data. I plan on creating a model which uses my ground-based LAI to establish a relationship or train my UAV imagery. I will ...
0
votes
0
answers
270
views
Detection of tomato areas from UAV images using ML
I have many UAV .tif images which they contain tomato plant in a farm, and between them there is separation with soil. So by searching on google I have found this paper https://www.mdpi.com/2072-4292/...
1
vote
1
answer
67
views
Deep machine learning to improve satellite spatial resolution
Are there currently technologies based on deep machine learning that can improve the spatial resolution of satellite images (e.g. Sentinel-2)?
An example of the use of such technology to reconstruct a ...
3
votes
1
answer
485
views
Using RandomForest for land use classification in Google Earth Engine: Training accuracy shows error
I am using RandomForest classification for my LULCC study. I have been successful in running the classification including getting the "validation accuracy" as 0.87. However, my "...
0
votes
1
answer
177
views
View values of clusters after unsupervised classification by NDVI in Google Earth Engine
I am creating unsupervised classifications of an area to detect landscape/vegetation change over time.
For each year:
I have created an NDVI of the area based on a composite of Landsat images ...
1
vote
1
answer
57
views
NameError in Machine learning with Open Data Cube notebook code
I am trying to run the "Machine learning with the Open Data Cube" using my own .shp file but seem to keep getting the same error. The only cell that I altered in the following link is number ...
6
votes
4
answers
282
views
Automated extraction of road network from points
I have a huge dataset containing about zillion of points representing tracking locations of cars on the roads.
I also have roads datasets to compare to (from 3 different sources), to use for training ...
2
votes
1
answer
320
views
What's the maximum number of data points allowed to train a classifier in Google Earth Engine?
What is the maximum number of data points allowed to train a classifier in Google Earth Engine (n columns * n rows)? I know there is some threshold that if you go above, you get a Computed value too ...
2
votes
0
answers
30
views
Find Optimal Subset of Feature Layer Based on Spatial Criteria & Attributes
I'm using a Census tract shapefile with their corresponding attributes of interest within ArcMap 10.7.1.
My project goal is to identify the subset of tracts that share a line segment while:
...
0
votes
0
answers
238
views
Google satellite basemap license
Where (if anywhere) can we buy a license to use Google satellite basemap as input to machine learning algorithms?
0
votes
0
answers
82
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
0
answers
561
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
0
answers
94
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
1
answer
86
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. ...
2
votes
2
answers
111
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
0
answers
80
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 ...
5
votes
4
answers
2k
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
1
answer
304
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
0
answers
24
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
1
answer
108
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
0
answers
108
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 ...
4
votes
1
answer
1k
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
1
answer
60
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
0
answers
27
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
0
answers
73
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
0
answers
94
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 ...