Python (research stack)

NumPy / Matplotlib / SciPy / Pandas cover every scenario in research data processing.

Details

The Python scientific computing stack is currently the most active ecosystem of research tools. Core libraries:

Matplotlib / Seaborn: publication-quality plotting
NumPy / SciPy: numerical computing
Pandas: tabular data processing
scikit-learn: machine learning
Rasterio / GDAL: raster remote sensing data
GeoPandas: vector GIS data

Managing environments with Miniconda is recommended.

Used in these research workflows

Remote sensing processingIntermediate

Remote Sensing Tree Height Estimation

A complete workflow for estimating forest tree height from LiDAR point clouds or multi-source remote sensing imagery using QGIS and Python.

QGISPython (research stack)

2–4 hours 5 stepsView workflow

Remote sensing processingIntermediate

Remote Sensing Image Classification

A workflow for preprocessing, building training samples, classifying and assessing accuracy for Sentinel, Landsat or drone imagery.

QGISGoogle Earth EnginePython (research stack)

3–6 hours 6 stepsView workflow

Image analysisIntermediate

Scientific Image Analysis

A workflow for segmenting, counting, measuring and analysing microscopy images, disease images, particle images and tissue sections.

ImageJ / FijiPython (research stack)

2–5 hours 5 stepsView workflow

Machine learningIntermediate

Machine Learning Modelling for Research

Starting from tabular or experimental data: prepare features, train, tune, validate and interpret models — suited to predictive modelling in research.

Python (research stack)scikit-learn

3–8 hours 5 stepsView workflow