The seasonal occurrence of hypoxia in the bottom waters of the northern Gulf of Mexico has been monitored for over 30 years (Rabalais et al., 2007; Rabalais et al., 2001). In general, the processes regulating the spatial and temporal variability of the hypoxic area in the region are attributed to variations in the nutrient load and the extension of the freshwater envelope generated by the Mississippi-Atchafalaya River system (Bianchi et al., 2010; Rowe & Chapman, 2002; Scavia et al., 2003). However, most mechanistic studies in the regional literature are concerned with the relationship between these two drivers and the full extent of hypoxia, while the internal variability and short-term shifts have been insufficiently investigated. Furthermore, the severity of hypoxia has often been equated to its areal extent, such that most modeling efforts are directed to estimate this quantity with accuracy. Official estimates of extent for managerial

Abstract. Offline advection schemes allow for low-computational-cost simulations using existing model output. This study presents the approach and assessment for passive offline tracer advection within the Regional Ocean Modeling System (ROMS). An advantage of running the code within ROMS itself is consistency in the numerics on- and offline. We find that the offline tracer model is robust: after about 14 d of simulation (almost 60 units of time normalized by the advection timescale), the skill score comparing offline output to the online simulation using the TS_U3HADVECTION and TS_C4VADVECTION (third-order upstream horizontal advection and fourth-order centered vertical advection) tracer advection schemes is 99.6 % accurate for an offline time step 20 times larger than the online time step as well as online output saved with a period below the advection timescale. For the MPDATA tracer advection scheme, accuracy is more variable with the offline time step and forcing input frequency choices, but it is still over 99 % for many reasonable choices. Both schemes are conservative. Important factors for maintaining high offline accuracy are outputting from the online simulation often enough to resolve the advection timescale, forcing offline using realistic vertical salinity diffusivity values from the online simulation, and using double precision to save results.

Abstract. Offline advection schemes allow for low computational cost simulations using existing model output. This study presents the approach and assessment for passive offline tracer advection within the Regional Ocean Modeling System (ROMS). An advantage of running the code within ROMS itself is consistency in the numerics on and offline. We find that the offline tracer model is robust: after about 14 days of simulation (almost 60 advection timescales), the skill score comparing offline output to the online simulation using the TS_U3HADVECTION and TS_C4VADVECTION (3rd-order upstream horizontal advection and 4th-order centered vertical advection) tracer advection schemes is 99.6 % accurate for an offline time step 20 times larger than online, and online output saved with a period below the advection timescale. For tracer advection scheme MPDATA, accuracy is more variable with offline time step and forcing input frequency choices, but is still over 99 % for many reasonable choices. Both schemes are conservative. Important factors for maintaining high offline accuracy are: outputting from the online simulation often enough to resolve the advection timescale, forcing offline using realistic vertical salinity diffusivity values from the online simulation, and using double precision to save results.

This study focuses on predicting harmful algal bloom (HAB) events in Lake Okeechobee, a shallow lake in Florida. A spatio-temporal deep learning model is employed to predict the levels of cyanobacteria Microcystis aeruginosa (M. aeruginosa) present in the lake for a single-day and a 14day prediction horizon. Datasets collected from remote sensing (i.e., satellite images from Jan. 2018 to Dec. 2020) and from a physics-based simulation model (i.e., daily simulation from Jan. 2018 to Dec. 2020) are available. Due to the low quality of remote sensing data caused by various environmental and technical issues, the two available datasets are fused together to create a multi-source hybrid dataset for deep learning model training. A convolutional long-short term memory (ConvLSTM) deep neural model is trained on the datasets, and the results of the predictions are compared to the true Cyanobacterial Index (CI) for that time period. Findings include 1) the deep learning model, ConvLSTM, shows promising performance for short-and mid-term HAB forecasting; and 2) the hybrid dataset that fuses remote sensing with physics-based modeling (a.k.a. modeling based on fundamental physical and biogeochemical principles) speeds up the model learning and improves its performance significantly. The proposed methodologies are reliable, and costeffective, and could be used to forecast algal bloom occurrences in shallow lakes with limited sparse observations.