Annie Lyu

Principal Data Scientist

Autodesk

Biography

In both my professional and personal life, I cherish deep connection, trust, exploration, and diversity. At work, I'm fueled by my passion for using data to tell compelling stories and express myself effectively. I find immense satisfaction in seeing my data narratives resonate with stakeholders beyond my field, empowering them to make informed decisions. I firmly believe that nurturing psychological safety within teams is the cornerstone of success.

Outside of work, I'm all about embracing offline and offscreen activities. You'll often find me hiking with my beloved dog Peony, checking out comedy shows, immersing myself in art, and enjoying live musical performances. These experiences recharge me and inspire my creativity.

Interests

Data Storytelling
Data Visualization
Statistical Learning

Education

PhD in Statistics, 2020

Iowa State University, United States
BSc in Statistics, 2015

Wuhan University, China

Experience

Data Scientist, Autodesk Construction Cloud

Autodesk

Aug 2020 – Present Toronto, Canada

Research Assistant, Center for Survey Statistics and Methodology

Iowa State University

Aug 2015 – Jun 2020 Ames, United States

Recent Posts

VISCOVER is now featured in the RStudio Shiny Gallery!

I am so happy to share the news that my R Shiny app viscover is now featured in the RStudio Shiny Gallery. 🎉 🎉 🎉 It's categorized into the Public Sector section in the Gallery due to its application to the soil survey data and cropland data layer maintained by the USDA. viscover takes its name from VIsulizing Soil and Crop data and their OVERlay. Although my motivation to develop

Annie Lyu

Feb 4, 2020 5 min read R

Fun blogdown in R to design a personal website

Inspired by David Robinson‘s keynote talk at the RStudio conference 2019 (summary in the following tweet), I decided to write a post about how I use Yihui‘s fantastic R package blogdown to develop my own personal website. When you’ve written the same code 3 times, write a function When you’ve given the same in-person advice 3 times, write a blog post — David Robinson (@drob) November 9, 2017 Well, there are a lot of useful references to check out.

Annie Lyu

Last updated on Jan 12, 2020 8 min read R

Fun Leaflet in R with NYC Squirrel Census Data

Anabelle introduced the NYC Squirrel Census data to me today. It also comes from the recommended dataset of #TidyTusday. Both of us adore squirrels 😍. The dataset contains variables which can tell when (Date) and where (longitude X and latitude Y) people saw a squirrel of certain age (Age) and fur color (Primary Fur Color) conducting some activities (Running, Climbing, Chasing, Eating, Foraging or Other Activities). Having some experience working with leaflet in R, I find it very interesting to visualize this data set on an interactive map.

Annie Lyu

Oct 29, 2019 3 min read R

2019暑期游记

个人网站上的第一篇中文博客献给值得纪念的2019年暑假，响应谢老大的号召，我网故我在。一个人的七天欧洲之旅因为参加一个国际会议，我短暂拜访了

Annie Lyu

Aug 24, 2019 8 min read life

Showcase my home-made dessert

🍰 🍰 🍰 dessert

Annie Lyu

Aug 30, 2018 1 min read life

See all posts

Featured Publications

Annie Lyu, Emily J. Berg, Heike Hofmann

July 2020 Biometrical Journal

Empirical Bayes small area prediction under a zero-inflated lognormal model with correlated random area effects

Demonstrated superior performance in predicting mean RUSLE2 erosion for South Dakota counties.

Code Dataset Slides DOI

Anabelle Laurent, Annie Lyu, Peter Kyveryga, David Makowski, Heike Hofmann, Fernando Miguez

July 2020 Research Synthesis Methods

Interactive web-based data visualization and analysis tool for synthetizing on-farm research networks data

ISOFAST, an interactive web tool developed using R Shiny, aimed at enhancing communication of on-farm trial results and aiding decision-making by farmers and agronomists through the synthesis of multi-site and multi-year trial data using a random-effects model.

Video DOI

Tyler M. Harms, Kevin T. Murphy, Annie Lyu, Shane S. Patterson, Karen E. Kinkead, Stephen J. Dinsmore, Paul W. Frese

March 2017 PLOS ONE

Using landscape habitat associations to prioritize areas of conservation action for terrestrial birds

Utilized long-term monitoring data and land cover datasets to model the probability of occupancy and colonization for 38 bird species, aiding in the prediction of species distributions on the Iowa landscape and providing valuable insights for conservation efforts amidst limited resources.

PDF Slides DOI

Shiny

Riichi Mahjong Calculator App

My first Shiny mobile app! A score calculator for Riichi Mahjong, a Japanese variant of the classic Chinese game.

viscover: visualize soil and crop data and their overlay

Enabling users to access and interact with the Cropland Data Layer (CDL) and Soil Data Layer (SDL), with seamless cross-referencing capabilities. Recognized in the RStudio Shiny Gallery.

iNtr: an interactive NRI table review tool

Enhancing efficiency in reviewing National Resource Inventory (NRI) estimates, enabling reviewers to compare and highlight critical data points, thereby accelerating the release of NRI estimates. Currently owned by the Center for Survey Statistics and Methodology (CSSM) at Iowa State University.

ISOFAST: ISA On-Farm Trial Summarization Tool

Facilitating farmers in navigating exploratory data analysis and statistical inference from on-farm trial data. Currently owned by the Iowa Soybean Association.

Iowa DNR MSIM - SGCN Modeling

Predicting the probabilities of occupancy, colonization, and extinction for 69 wild species in Iowa, offering interactive web-based access to prediction maps to aid land managers. Developed for the Iowa Department of Natural Resources.

Systematic Sampling Illustration

Facilitating instant experimentation to clarify the impact of sampling frame ordering on the sampling distribution of a systematic sample. Developed for the STAT421 (Survey Statistics) course at Iowa State University.