Is this you? As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.
Claim your profile
Articles by Aleksei Rozanov
Microbial diversity and production of milk spirit using traditional Buryat fermentation and distillation technologies
Abstract Distilled fermented milk beverages are rare in food technology, despite the global prevalence of plant-based spirits. Currently, the production of distilled strong alcoholic beverages from fermented milk using traditional technologies is known only among Mongolic-speaking peoples and their Siberian neighbors. This study provides the first interdisciplinary analysis of darasun, a traditional Buryat spirit made from fermented milk beverage khurenge in Southern Siberia.
Regression Trees Explained: The Most Intuitive Intoduction
Regression Tree in Python from Scratch The field of machine learning is often framed around two dominant classes of models: neural networks (NNs) and tree-based methods. Early in my ML journey, I found it surprisingly easy to build an intuition for how neural nets work. You take a weighted sum of your inputs, pass it through a non-linear activation function, and repeat across layers. Simple enough — at least on the surface.
How To Plot Chaos? Butterflyğ¦ Effect in Python
Lorenz Attractor in 3D Aleksei Rozanov · Follow 6 min read · -- Image by author. Let me start with a bold claim: nature is the greatest artist of all time. Its masterpieces are everywhere, even if theyâre not always obvious in our daily lives. Yet, the most inspiring works often remain hidden, and itâs science that allows us to reveal them.
My Freelance Experience as a Geo Data Scientist on UpWork after 10 Months
How to get clients, reviews and stable income Around 10 months ago I decided that after several years of purely academic professional experience I want to try some freelancing/consulting. However, I found that my skill set was somewhat rare and weird. On the one hand, my masters degree in Big Data and Machine Learning equipped me with a range of very helpful tools and knowledge of industrial data processing, modeling and analysis. However, I was extremely far from calling myslef an expert.
What’s Inside a Neural Network?
Plotting surface of error in 3D using PyTorch🔥 In my senior year of undergrad, like many other students, I had to choose a topic for my bachelor’s thesis. My major was hydrometeorology, so I initially considered researching a problem related to climate modeling. Fortunately, my advisor, Dr. Gribanov, suggested exploring a completely new direction I knew nothing about at the time — applying Neural Networks to upscale terrestrial carbon fluxes.
Can You See the War from Space?
Case study of the Russian-Ukrainian war Almost three years have passed since Russia invaded Ukraine’s territory on February 24th, 2024. This bloody war has destroyed or somehow affected dozens of thousands of families on both sides of the conflict. There is plenty of evidence across the internet shedding light on human suffering and pain brought by this war, one of the main sources of data being aerial and space imagery.
DBSCAN, Explained in 5 Minutes
Fastest implementation in pythonš Whatās DBSCAN [1]? How to build it in python? There are many articles covering this topic, but I think the algorithm itself is so simple and intuitive that itās possible to explain its idea in just 5 minutes, so letās try to do that. DBSCAN = Density-Based Spatial Clustering of Applications with Noise What does it mean? The algorithm searches for clusters inside the data based on the spatial distance between objects.
Simulating Wildfires in a Forestš„
Simulating any natural process is always quite a challenging task, especially when we are talking about weather and climate. In essence, a so called process-based model always relies on some set of assumptions allowing relatively simple description of a certain environment. These assumptions are a necessity since we can't account for every process or a trajectory of each object/molecule/particle.
5 Python Features to Make Your Code More Advanced
Python has been my main programming tool for the last 2 years, and I'm sure it will stay the one for years, despite the fact that I have some basic knowledge of C++, JS, MatLab and R. The reason for that is its user-friendliness, intuitiveness and, of course, the quality and popularity of the machine learning frameworks built in python.
Erasing Clouds from Satellite Imagery Using GANs (Generative Adversarial Networks)
The idea of Generative Adversarial Networks, or GANs, was introduced by Goodfellow and his colleagues [1] in 2014, and shortly after that became extremely popular in the field of computer vision and image generation. Despite the last 10 years of rapid development within the domain of AI and growth of the number of new algorithms, the simplicity and brilliance of this concept are still extremely impressive.
LA Crime: Now in 3D (No Glasses Required)
Visualizing crime geodata in python In my opinion, one of the best features geo data possesses is its capability for 3D visualization. However, due to the amount of computational resources needed for such calculations, it’s really rarely performed in python (often JavaScript and its libraries used as alternatives). In one of my previous articles I shared six python packages which allow creation of beautiful static and interactive maps, yet only in 2D space.
Now in 3D (No Glasses Required)
import numpy as np import pandas as pd import xarray as xr import geopandas as gpd import random import math import matplotlib.pyplot as plt from shapely import Point import cartopy import cartopy.crs as ccrs import cartopy.feature as cfeature import warnings warnings.filterwarnings('ignore') recent = pd.read_csv('./LA Crimes/Crime_Data_from_2020_to_Present.csv')[['LAT', 'LON']] old = pd.read_csv('./LA Crimes/Crime_Data_from_2010_to_2019.csv')[['LAT', 'LON']] df = pd.concat([old, recent]) df...
How to Create Your Own CV Dataset Using Satellite Imagery: Wildfires from Space
Collecting images to train CNNs Have you ever had this idea that a pet project on the application of ML to satellite images might significantly strengthen your data science portfolio? Or have you trained some models based on datasets developed by other people but not your own?
You’ve Got a Time Series. Now What? Original
How to do exploratory data analysis of a time series One of the most popular types of data is a time series. Videos, images, pixels, signals, literally anything having a time component could be turned into it. Formally, a time series is a sequence of historical measurements of an observable variable at equal time intervals. In this article I want to suggest a small pipeline which anyone can use when analyzing a time series.
3 Popular Methods for Spatial Interpolation
From scratch, in Python Interpolation is a quite common mathematical concept, which is used not only by data scientists, but also people from a vast range of fields. However, when dealing with geospatial data, interpolation gets more complicated, since you need to create a representative grid based on several often sparse observations. Before diving into geospatial part, let’s have a brief recap on linear interpolation.
3 Best Methods for Spatial Interpolation
From scratch, in Python Interpolation is a quite common mathematical concept, which is used not only by data scientists, but also people from a vast range of fields. However, when dealing with geospatial data, interpolation gets more complicated, since you need to create a representative grid based on several often sparse observations. Before diving into geospatial part, let’s have a brief recap on linear interpolation.
Semantic Segmentation of Remote Sensing Imagery using k-Means
From scratch in python🐍 One of the most simple and genius ML models, in my opinion, is k-Means clustering. It relates to the group of unsupervised learning algorithms and is capable of finding patterns inside an unlabeled dataset. The most pleasant feature is that it lacks complicated math, and basically any high school student can successfully implement and use this method.
Semantic Segmentation of Remote Sensing Imagery using k-Means
From scratch in python🐍 One of the most simple and genius ML models, in my opinion, is k-Means clustering. It relates to the group of unsupervised learning algorithms and is capable of finding patterns inside an unlabeled dataset. The most pleasant feature is that it lacks complicated math, and basically any high school student can successfully implement and use this method.
How can a sea disappear? Case study of the Aral Sea using Python and MODIS data.
Let’s create a timelapse and check if it’s true! Can you imagine that a SEA disappears because of human actions? Sounds like an excellent catch for a film, but, unfortunately, it’s the reality. Once in the Central East there was the Aral Sea, lying between modern Kazakhstan and Uzbekistan.
Weather And Climate Data For A Data Science Project. Where to take?
Temperature and precipitation time series are extremely popular in many Data Science projects and tutorials, however it’s often unclear where and how to acquire them. I’m writing this article to help you to navigate through different sources and types of meteorological data and build your own dataset, which would describe some real-world problem and make sense among other works in your portfolio. First thing first, you need to start with the problem conceptualization.
Particle Swarm Optimization (PSO) from scratch. Simplest explanation in python Original
How to implement PSO Before talking about swarms and particles, let’s briefly discuss optimization itself. Basically, optimization is the process of finding the minima or maxima of some function. For instance, when you need to get to your office ASAP and think about which way is the fastest, you’re optimizing your route (in this case it’s a function). In math, there are literally hundreds of ways of optimization, and among them a sub-group called nature-inspired exists.
6 python libraries to make beautiful maps
At some point any Data Scientist faces the need to analyze or model geo spatial data, and it can’t be done without the crucial visual part. As I’m a huge map-lover, I’m glad to share with you these 6 great libraries for making informative and stylish maps. Some of the libraries I shared here are more suitable for static visualizations, others for interactive ones, so the range of problems they can tackle is wide.
Show More
loading
Actions
Is this you?
As a journalist, you can create a free Muck Rack account to customize your profile, list your contact preferences, and upload a portfolio of your best work.Get in touch with Aleksei
Contact Aleksei, search articles and posts on X, monitor coverage, and track replies from one place.
Learn more about Muck Rack