Thomas Lees
YOU?
Author Swipe
View article: A thinner-than-present West Antarctic Ice Sheet in the southern Weddell Sea Embayment during the Holocene
A thinner-than-present West Antarctic Ice Sheet in the southern Weddell Sea Embayment during the Holocene Open
Making accurate measurements and predictions of the West Antarctic Ice Sheet’s (WAIS) contribution to present and future sea-level rise fundamentally depends on knowing its trajectory over the last few thousand years. We present new in sit…
View article: The Turkana Jet Diurnal Cycle in Observations and Reanalysis
The Turkana Jet Diurnal Cycle in Observations and Reanalysis Open
The Turkana jet is an equatorial low-level jet (LLJ) in East Africa. The jet influences both flooding and droughts, and powers Africa’s largest wind farm. Much of what we know about the jet, including the characteristics of its diurnal cyc…
View article: Using a Deep Learning Framework to Forecast Reservoir Water Availability in India
Using a Deep Learning Framework to Forecast Reservoir Water Availability in India Open
This paper introduces a machine learning-based model to forecast reservoir water volumes in India. In areas with high water stress, having access to timely information on forecasted water availability could help decision-makers avoid the r…
View article: Hydrological concept formation inside long short-term memory (LSTM) networks
Hydrological concept formation inside long short-term memory (LSTM) networks Open
Neural networks have been shown to be extremely effective rainfall-runoff models, where the river discharge is predicted from meteorological inputs. However, the question remains: what have these models learned? Is it possible to extract i…
View article: Wave2Web: Near-real-time reservoir availability prediction for water security in India
Wave2Web: Near-real-time reservoir availability prediction for water security in India Open
By 2050, over half the world's population will live in water-stressed areas. Medium-term drought forecasting can help planners avoid ``day-zero'' events and adapt to climate change. Machine learning-based precipitation-runoff modelling ena…
View article: Observations of the Turkana Jet and the East African Dry Tropics: The RIFTJet Field Campaign
Observations of the Turkana Jet and the East African Dry Tropics: The RIFTJet Field Campaign Open
The Turkana low-level jet (LLJ) is an intrinsic part of the African climate system. It is the principle conduit for water vapor transport to the African interior from the Indian Ocean, and droughts in East Africa tend to occur when the jet…
View article: Reply on CC1
Reply on CC1 Open
Neural networks have been shown to be extremely effective rainfall-runoff models, where the river discharge is predicted from meteorological inputs. However, the question remains, what have these models learned? Is it possible to extract i…
View article: Reply on RC1
Reply on RC1 Open
Neural networks have been shown to be extremely effective rainfall-runoff models, where the river discharge is predicted from meteorological inputs. However, the question remains, what have these models learned? Is it possible to extract i…
View article: Reply on RC2
Reply on RC2 Open
Neural networks have been shown to be extremely effective rainfall-runoff models, where the river discharge is predicted from meteorological inputs. However, the question remains, what have these models learned? Is it possible to extract i…
View article: Deep Learning for Vegetation Health Forecasting: A Case Study in Kenya
Deep Learning for Vegetation Health Forecasting: A Case Study in Kenya Open
East Africa has experienced a number of devastating droughts in recent decades, including the 2010/2011 drought. The National Drought Management Authority in Kenya relies on real-time information from MODIS satellites to monitor and respon…
View article: Supplement on CC1
Supplement on CC1 Open
Abstract. Neural networks have been shown to be extremely effective rainfall-runoff models, where the river discharge is predicted from meteorological inputs. However, the question remains: what have these models learned? Is it possible to…
View article: Comment on hess-2021-566
Comment on hess-2021-566 Open
Abstract. Neural networks have been shown to be extremely effective rainfall-runoff models, where the river discharge is predicted from meteorological inputs. However, the question remains, what have these models learned? Is it possible to…
View article: Hydrological Concept Formation inside Long Short-Term Memory (LSTM) networks
Hydrological Concept Formation inside Long Short-Term Memory (LSTM) networks Open
Neural networks have been shown to be extremely effective rainfall-runoff models, where the river discharge is predicted from meteorological inputs. However, the question remains, what have these models learned? Is it possible to extract i…
View article: Hydrological Concept Formation inside Long Short-Term Memory (LSTM) networks
Hydrological Concept Formation inside Long Short-Term Memory (LSTM) networks Open
Datasets for Linear Probe Analysis presented in the paper: Hydrological Concept Formation inside Long Short-Term Memory (LSTM) networks by Lees et al (2021).
View article: Benchmarking data-driven rainfall–runoff models in Great Britain: a comparison of long short-term memory (LSTM)-based models with four lumped conceptual models
Benchmarking data-driven rainfall–runoff models in Great Britain: a comparison of long short-term memory (LSTM)-based models with four lumped conceptual models Open
Long short-term memory (LSTM) models are recurrent neural networks from the field of deep learning (DL) which have shown promise for time series modelling, especially in conditions when data are abundant. Previous studies have demonstrated…
View article: Nonstationary weather and water extremes: a review of methods for their detection, attribution, and management
Nonstationary weather and water extremes: a review of methods for their detection, attribution, and management Open
Hydroclimatic extremes such as intense rainfall, floods, droughts, heatwaves, and wind or storms have devastating effects each year. One of the key challenges for society is understanding how these extremes are evolving and likely to unfol…
View article: Reply on RC2
Reply on RC2 Open
Abstract. Long short-term memory (LSTM) models are recurrent neural networks from the field of deep learning (DL) which have shown promise for time series modelling, especially in conditions when data are abundant. Previous studies have d…
View article: Reply on RC1
Reply on RC1 Open
Abstract. Long short-term memory (LSTM) models are recurrent neural networks from the field of deep learning (DL) which have shown promise for time series modelling, especially in conditions when data are abundant. Previous studies have d…
View article: Reply on CC2
Reply on CC2 Open
Abstract. Long short-term memory (LSTM) models are recurrent neural networks from the field of deep learning (DL) which have shown promise for time series modelling, especially in conditions when data are abundant. Previous studies have d…
View article: Overview of Proposed Manuscript Changes based on Reviewer Comments
Overview of Proposed Manuscript Changes based on Reviewer Comments Open
Abstract. Long short-term memory (LSTM) models are recurrent neural networks from the field of deep learning (DL) which have shown promise for time series modelling, especially in conditions when data are abundant. Previous studies have d…
View article: Overview of Proposed Manuscript Changes based on Reviewer Comments
Overview of Proposed Manuscript Changes based on Reviewer Comments Open
Abstract. Long short-term memory (LSTM) models are recurrent neural networks from the field of deep learning (DL) which have shown promise for time series modelling, especially in conditions when data are abundant. Previous studies have d…
View article: Reply on RC3
Reply on RC3 Open
Abstract. Long short-term memory (LSTM) models are recurrent neural networks from the field of deep learning (DL) which have shown promise for time series modelling, especially in conditions when data are abundant. Previous studies have d…
View article: Comment on hess-2021-127
Comment on hess-2021-127 Open
Abstract. Long short-term memory (LSTM) models are recurrent neural networks from the field of deep learning (DL) which have shown promise for time series modelling, especially in conditions when data are abundant. Previous studies have d…
View article: Comment on hess-2021-127
Comment on hess-2021-127 Open
Abstract. Long short-term memory (LSTM) models are recurrent neural networks from the field of deep learning (DL) which have shown promise for time series modelling, especially in conditions when data are abundant. Previous studies have d…
View article: Comment on hess-2021-127
Comment on hess-2021-127 Open
Abstract. Long short-term memory (LSTM) models are recurrent neural networks from the field of deep learning (DL) which have shown promise for time series modelling, especially in conditions when data are abundant. Previous studies have d…
View article: Reply on CC2
Reply on CC2 Open
Abstract. Long short-term memory (LSTM) models are recurrent neural networks from the field of deep learning (DL) which have shown promise for time series modelling, especially in conditions when data are abundant. Previous studies have d…
View article: Reply on CC1
Reply on CC1 Open
Abstract. Long short-term memory (LSTM) models are recurrent neural networks from the field of deep learning (DL) which have shown promise for time series modelling, especially in conditions when data are abundant. Previous studies have d…
View article: Comment on hess-2021-127
Comment on hess-2021-127 Open
Abstract. Long short-term memory (LSTM) models are recurrent neural networks from the field of deep learning (DL) which have shown promise for time series modelling, especially in conditions when data are abundant. Previous studies have d…
View article: Benchmarking Data-Driven Rainfall-Runoff Models in GreatBritain: A comparison of LSTM-based models with four lumpedconceptual models
Benchmarking Data-Driven Rainfall-Runoff Models in GreatBritain: A comparison of LSTM-based models with four lumpedconceptual models Open
Long short-term memory models (LSTMs) are recurrent neural networks from the emerging field of Deep Learning (DL), which have shown recent promise when predicting time-series especially when data are abundant. Rainfall-runoff modelling pre…