Doctoral Spatial statistics integrating IoT field sensor data and remote sensing data

Doctoral Candidate Spatial statistics for integrating IoT field sensor data and remote sensing data for nature-inclusive solutions in tree crop diseases  Looking for a job that matters? Join the university of technology that puts people first – and shape new opportunities both for yourself and for ou...
The University of Twente, Faculty ITC, wishes to increase the number of women in the faculty to have a more balanced staff profile. During all phases of the selection process, we will therefore prioritize selecting women who fit the profile.
The Dutch government, through the Ministry of Education, Culture and Science, has responded to the current global environmental challenges by establishing sector plan positions in critical scientific domains. At the Department of Environmental Resources, one of our activities is to address these challenges by developing and applying Geostatistical models for bridging knowledge gaps, data scarcity and uncertainty gaps, and governance gaps related to monitoring the environment on which humans depend.
A part of this is  spatial statistics of sensor data integration for nature-inclusive solutions   for  monitoring stress and diseases of tree crops .  Tree crops like cocoa, apart from their direct economic functions for smallholder farmers, sit at the intersection of many beneficial ecological functions (including carbon sequestration and cultural identity). However, these functions are threatened by environmental stressors and diseases such as Cocoa Swollen Shoot Virus (CSSV) disease, which depend on the complex web of interactions between and within above-ground and below-ground biotic and abiotic factors.

The prevailing data and methodological gaps that have perpetuated knowledge gaps in the spatial and spatiotemporal patterns of tree disease, and the widened governance gaps of farms, have motivated this topic.
You will develop spatial statistical methods to integrate ground-based IoT sensor data, remote sensing data, and in-situ data for mapping the spatial trends of cocoa diseases. You will be involved in setting up an IoT sensor network in cocoa farms in Ghana. You are expected to address data integration challenges, including (1) spatial misalignment of networks, (2) temporal misalignments of observations, (2) probabilistic or likelihood misalignments, and (3) data quality issues, such as uncertainties in measurements, sparsity of network coverage resulting in small N, missing data resulting from malfunction of sensors, and outliers.

For the purposes of evaluating model transferability, you will make a comparison with other economically important tree crops in food forests in the Netherlands. You will design a measurement setup for cocoa trees and review the wide range of applications of IoT sensors, their uncertainties, and the observable variables above and below ground that are important for predicting tree crop diseases and stresses.

You will also explore simulation scenarios to evaluate the impact of indigenous and formal farming management practices on plant diseases.

Your profile   An MSc related to geoinformation science and earth observation, spatial and spatiotemporal modelling, spatial statistics, and/or machine learning. You enjoy applying these modelling skills to analyse and explain interactions within environmental and ecological systems
Able to handle and integrate multi-temporal and multi-spatial data from multiple sources, including earth observation data, IoT-based sensor data, and in situ data
Comfortable with programming or scripting in Python or R for data analysis and for bringing your models to the data
Good communication skills and an excellent command of the English language
Enjoy engaging in team science with project and…