Year of Award


Document Type


Degree Type

Master of Science (MS)

Degree Name

Computer Science

Department or School/College

Computer Science

Committee Chair

Douglas Brinkerhoff

Commitee Members

Douglas Brinkerhoff, Jesse Johnson, Marco Maneta


machine learning, neural networks, mapping, irrigation


University of Montana

Subject Categories

Artificial Intelligence and Robotics | Environmental Monitoring | Natural Resources Management and Policy | Water Resource Management


Accurate maps of irrigation are essential for understanding and managing water resources in light of a warming climate. We present a new method for mapping irrigation and apply it to the state of Montana over the years 2000-2019. The method is based on an ensemble of convolutional neural networks that only rely on raw Landsat surface reflectance data. The ensemble of networks method learns to mask clouds and ignore Landsat 7 scan-line failures without supervision, reducing the need for preprocessing data or feature engineering. Unlike other approaches to mapping irrigation, the method doesn't use other mapping products like the Cropland Data Layer or the National Land Cover Dataset, removing the biases inherent in using those products. We evaluate our method and compare it to existing maps of irrigation on novel spatially explicit ground truth data, finding that our method outperforms other methods of mapping irrigation in Montana in terms of overall accuracy and precision. We find that our method agrees better statewide with the USDA National Agricultural Statistics Survey estimates of irrigated area compared to other methods, and has far fewer errors of commission in rainfed agriculture areas. In addition, our method produces uncertainties for predictions of irrigated land, and we find that the neural networks have large uncertainty in some misclassified areas. The methodology has the potential to be applied across the entire United States and for the complete Landsat record.



© Copyright 2020 Thomas Henry Colligan IV