Oivind Kare Kjerstad
Oivind Kare Kjerstad has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Roger Skjetne
Department of Marine Technology, Norwegian University of Science and Technology, Trondheim, Norway
3 shared publications - Houxiang Zhang
Department of Ocean Operations and Civil Engineering, Norwegian University of Science and Technology, Larsgaardsvegen 2, 6009 Aalesund, Norway
2 shared publications - Andrew R. Teel
Electrical and Computer Engineering Department, University of California, Santa Barbara, CA, USA
1 shared publication - Beatriz Sanguino1 shared publication
- Bjornar Vik
Kongsberg Maritime, AS, Aalesund, Norway
1 shared publication Christoffer Thorvaldsen
1 shared publication
Latest Publications
- Open Access
- 21 August 2026
- Published by MDPI AG in Environments
- Vol. 13 (8) , 463
Explainable Multiclass Forecasting of Tourism-Oriented Seawater Quality Dynamics Using High-Frequency Coastal Monitoring
Recreational coastal waters are increasingly affected by urbanization, maritime activities, and tourism, creating a need for predictive tools that support proactive water quality management. This study proposes an explainable machine learning framework for forecasting near-future changes in the Tourism-Oriented Seawater Quality Index (SeaWQI-T) using high-frequency seawater monitoring data collected in the Gulf of Vlorë, Albania. A summer monitoring campaign (June–August 2025) produced 102,988 physicochemical observations from six monitoring stations using an unmanned surface vehicle equipped with a Horiba U53 multiparameter sonde. Following quality control and temporal aggregation, the data were used to formulate a multiclass forecasting problem (decrease, stable, or increase), and Logistic Regression, Random Forest, and Extreme Gradient Boosting (XGBoost) models were evaluated across multiple forecasting horizons. XGBoost achieved the best validation performance, while Random Forest demonstrated superior generalization on the independent test dataset and provided the most stable explainability results. SHapley Additive exPlanations (SHAP) identified SeaWQI-T dynamics, turbidity, dissolved oxygen, and oxidation–reduction potential as the most influential predictors. The proposed framework demonstrates that integrating explainable machine learning with autonomous high-frequency monitoring can provide accurate, interpretable forecasts to support intelligent coastal recreation management and sustainable tourism planning.
- 21 August 2026
- Published by MDPI AG in Environments
- Vol. 13 (8) , 463
Open AccessExplainable Multiclass Forecasting of Tourism-Oriented Seawater Quality Dynamics Using High-Frequency Coastal Monitoring
Recreational coastal waters are increasingly affected by urbanization, maritime activities, and tourism, creating a need for predictive tools that support proactive water quality management. This study proposes an explainable machine learning framework for forecasting near-future changes in the Tourism-Oriented Seawater Quality Index (SeaWQI-T) using high-frequency seawater monitoring data collected in the Gulf of Vlorë, Albania. A summer monitoring campaign (June–August 2025) produced 102,988 physicochemical observations from six monitoring stations using an unmanned surface vehicle equipped with a Horiba U53 multiparameter sonde. Following quality control and temporal aggregation, the data were used to formulate a multiclass forecasting problem (decrease, stable, or increase), and Logistic Regression, Random Forest, and Extreme Gradient Boosting (XGBoost) models were evaluated across multiple forecasting horizons. XGBoost achieved the best validation performance, while Random Forest demonstrated superior generalization on the independent test dataset and provided the most stable explainability results. SHapley Additive exPlanations (SHAP) identified SeaWQI-T dynamics, turbidity, dissolved oxygen, and oxidation–reduction potential as the most influential predictors. The proposed framework demonstrates that integrating explainable machine learning with autonomous high-frequency monitoring can provide accurate, interpretable forecasts to support intelligent coastal recreation management and sustainable tourism planning.
- Open Access
- 3 August 2026
- Published by Elsevier in Ocean Engineering
- Vol. 365
Time-consistent adaptive sampling RRT* for COLREG-compliant maritime collision avoidance
- 3 August 2026
- Published by Elsevier in Ocean Engineering
- Vol. 365
Open AccessTime-consistent adaptive sampling RRT* for COLREG-compliant maritime collision avoidance
- Open Access
- 21 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control Systems Technology
- Vol. 32 (3) , 1048-1056
A Resetting Observer for Linear Time-Varying Systems With Application to Dynamic Positioning of Marine Surface Vessels
This brief presents a resetting observer for linear time-varying (LTV) systems. The motivation for the observer is better handling of unmodeled dynamics and reactiveness to external disturbances without compromising steady-state performance. A reset is triggered if the output estimation error exceeds predefined bounds. The proposed observer uses a finite-time observer (FTO) approach to calculate corrected state estimates after a reset is triggered. The FTO equations are derived for LTV systems, and a method for calculating the state transition matrices online is presented. The observer equations are formulated in a hybrid dynamical systems framework, and sufficient conditions for uniform global preexponential stability are given. The method is applied to observer design for dynamic positioning (DP) of marine surface vessels. Numerical simulations as well as model scale experiments of this application show promising results, with improved transient performance compared to state-of-the-art observers.
- 21 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Control Systems Technology
- Vol. 32 (3) , 1048-1056
Open AccessA Resetting Observer for Linear Time-Varying Systems With Application to Dynamic Positioning of Marine Surface Vessels
This brief presents a resetting observer for linear time-varying (LTV) systems. The motivation for the observer is better handling of unmodeled dynamics and reactiveness to external disturbances without compromising steady-state performance. A reset is triggered if the output estimation error exceeds predefined bounds. The proposed observer uses a finite-time observer (FTO) approach to calculate corrected state estimates after a reset is triggered. The FTO equations are derived for LTV systems, and a method for calculating the state transition matrices online is presented. The observer equations are formulated in a hybrid dynamical systems framework, and sufficient conditions for uniform global preexponential stability are given. The method is applied to observer design for dynamic positioning (DP) of marine surface vessels. Numerical simulations as well as model scale experiments of this application show promising results, with improved transient performance compared to state-of-the-art observers.
- 15 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Oceanic Engineering
- Vol. 48 (1) , 27-42
Inertial Navigation Aided by Ultra-Wideband Ranging for Ship Docking and Harbor Maneuvering
This article presents an inertial navigation system aided by local ranging measurements derived from an ultra-wideband system. The system consists of one onboard tag and several onshore anchors. It is motivated by the need to complement satellite systems in harbor areas to reduce the risk of localization dropout during high precision closed-loop maneuvering and docking of ships as it may imply severe consequences. The proposed state estimation algorithm includes ranging bias to compensate for minor inaccuracies originating mostly from tag and anchor processing time. The complete ultra-wideband aided inertial navigation system is validated using full-scale measurements collected during multiple dockings of a passenger ferry in Trondheim, Norway. The results show that the proposed localization system has comparable performance to state-of-the art inertial navigation systems aided by real-time kinematic satellite position measurements. Thus, it offers a viable alternative and complement which may contribute to safe and efficient high precision closed-loop maneuvering and docking of marine vessels.
- 15 September 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Oceanic Engineering
- Vol. 48 (1) , 27-42
Inertial Navigation Aided by Ultra-Wideband Ranging for Ship Docking and Harbor Maneuvering
This article presents an inertial navigation system aided by local ranging measurements derived from an ultra-wideband system. The system consists of one onboard tag and several onshore anchors. It is motivated by the need to complement satellite systems in harbor areas to reduce the risk of localization dropout during high precision closed-loop maneuvering and docking of ships as it may imply severe consequences. The proposed state estimation algorithm includes ranging bias to compensate for minor inaccuracies originating mostly from tag and anchor processing time. The complete ultra-wideband aided inertial navigation system is validated using full-scale measurements collected during multiple dockings of a passenger ferry in Trondheim, Norway. The results show that the proposed localization system has comparable performance to state-of-the art inertial navigation systems aided by real-time kinematic satellite position measurements. Thus, it offers a viable alternative and complement which may contribute to safe and efficient high precision closed-loop maneuvering and docking of marine vessels.
- Open Access
- 20 April 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 4 (99) , 2656-2669
Disturbance Rejection by Acceleration Feedforward for Marine Surface Vessels
Acceleration signals have a powerful disturbance rejection potential in rigid body motion control, as they carry a measure proportional to the resulting force. Yet, they are seldom used, since measuring, decoupling, and utilizing the dynamic acceleration in the control design is not trivial. This paper discusses these topics and presents a solution for marine vessels building on conventional methods together with a novel control law design, where the dynamic acceleration signals are used to form a dynamic referenceless disturbance feedforward compensation. This replaces conventional integral action and enables unmeasured external loads and unmodel dynamics to be counteracted with low time lag. A case study shows the feasibility of the proposed design using experimental data and closed-loop high fidelity simulations of dynamic positioning in a harsh cold climate environment with sea-ice.
- 20 April 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 4 (99) , 2656-2669
Open AccessDisturbance Rejection by Acceleration Feedforward for Marine Surface Vessels
Acceleration signals have a powerful disturbance rejection potential in rigid body motion control, as they carry a measure proportional to the resulting force. Yet, they are seldom used, since measuring, decoupling, and utilizing the dynamic acceleration in the control design is not trivial. This paper discusses these topics and presents a solution for marine vessels building on conventional methods together with a novel control law design, where the dynamic acceleration signals are used to form a dynamic referenceless disturbance feedforward compensation. This replaces conventional integral action and enables unmeasured external loads and unmodel dynamics to be counteracted with low time lag. A case study shows the feasibility of the proposed design using experimental data and closed-loop high fidelity simulations of dynamic positioning in a harsh cold climate environment with sea-ice.
- Open Access
- 1 January 2015
- Published by Elsevier in IFAC-PapersOnLine
- Vol. 48 (16) , 248-253
A Tension-based Position Estimation Approach for Moored Marine Vessels
- 1 January 2015
- Published by Elsevier in IFAC-PapersOnLine
- Vol. 48 (16) , 248-253
Open AccessA Tension-based Position Estimation Approach for Moored Marine Vessels