TY - JOUR
T1 - Predictive modeling of Ulva sp. growth and chemical composition in an outdoor air-mixed bioreactor under natural environmental conditions
T2 - A machine learning approach
AU - Gelashvili, Rati
AU - Chemodanov, Alexander
AU - Obolski, Uri
AU - Yakhini, Zohar
AU - Golberg, Alexander
N1 - Publisher Copyright:
© 2024 Elsevier B.V.
PY - 2025/1
Y1 - 2025/1
N2 - Approximately 35 million tons of wet macroalgae were harvested from aquaculture in 2020, and its cultivation is rapidly increasing. However, annual variability in yield and chemical composition due to natural environmental conditions makes cost-benefit analysis difficult, hindering profitable macroalgae cultivation. This study aims to develop models for predicting the growth and chemical composition of the green seaweed Ulva sp. based on measurable environmental variables. We used Forward Selection Search (FSS), the Ordinary Least Squares (OLS) best subset approach, and LASSO to develop a prediction model from two years of experimental measurements of Ulva sp. biomass growth and chemical composition in Mikhmoret, Israel. The best predictive model for fresh mass achieved an R2 of 0.77 with a Mean Absolute Percentage Error (MAPE) of 32 %. For dry mass, the R2 was 0.75 with a significantly higher MAPE of 62 %. The prediction for ash-free dry mass yielded an R2 of 0.6 and a Root Mean Square Error (RMSE) of 0.62. Carbon content prediction attained an R2 of 0.70 with an RMSE of 0.49, while nitrogen content prediction resulted in an R2 of 0.69 with an RMSE of 0.56. Our study demonstrates the potential of using machine learning to analyze seagricultural data and understand the yield and chemical composition in Ulva sp. These results could lead to the development of optimized cultivation techniques for large-scale seaweed farming.
AB - Approximately 35 million tons of wet macroalgae were harvested from aquaculture in 2020, and its cultivation is rapidly increasing. However, annual variability in yield and chemical composition due to natural environmental conditions makes cost-benefit analysis difficult, hindering profitable macroalgae cultivation. This study aims to develop models for predicting the growth and chemical composition of the green seaweed Ulva sp. based on measurable environmental variables. We used Forward Selection Search (FSS), the Ordinary Least Squares (OLS) best subset approach, and LASSO to develop a prediction model from two years of experimental measurements of Ulva sp. biomass growth and chemical composition in Mikhmoret, Israel. The best predictive model for fresh mass achieved an R2 of 0.77 with a Mean Absolute Percentage Error (MAPE) of 32 %. For dry mass, the R2 was 0.75 with a significantly higher MAPE of 62 %. The prediction for ash-free dry mass yielded an R2 of 0.6 and a Root Mean Square Error (RMSE) of 0.62. Carbon content prediction attained an R2 of 0.70 with an RMSE of 0.49, while nitrogen content prediction resulted in an R2 of 0.69 with an RMSE of 0.56. Our study demonstrates the potential of using machine learning to analyze seagricultural data and understand the yield and chemical composition in Ulva sp. These results could lead to the development of optimized cultivation techniques for large-scale seaweed farming.
KW - Marine macroalgae/seaweed
KW - Onshore biomass production
KW - Predictive modeling
KW - Production optimization
KW - Ulva rigida
UR - http://www.scopus.com/inward/record.url?scp=85212832535&partnerID=8YFLogxK
U2 - 10.1016/j.algal.2024.103832
DO - 10.1016/j.algal.2024.103832
M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???
AN - SCOPUS:85212832535
SN - 2211-9264
VL - 85
JO - Algal Research
JF - Algal Research
M1 - 103832
ER -