Effective observation of the ocean is vital for studying and assessing the state and evolution of the marine ecosystem, and for evaluating the impact of human activities. However, obtaining comprehensive oceanic measurements across temporal and spatial scales and for different biogeochemical variables remains challenging. Autonomous oceanographic instruments, such as Biogeochemical (BCG) Argo profiling floats, have helped expand our ability to obtain subsurface and deep-ocean measurements, but measuring biogeochemical variables such as nutrient concentration still remains more demanding and expensive than measuring physical variables. Therefore, developing methods to estimate marine biogeochemical variables from high-frequency measurements is very much needed. Current Neural Network (NN) models developed for this task are based on a Multilayer Perceptron (MLP) architecture, trained over punctual pairs of input-output features. However, MLPs lack awareness of the typical shape of biogeochemical variable profiles they aim to infer, resulting in irregularities such as jumps and gaps when used for the prediction of vertical profiles. In this study, we evaluate the effectiveness of a one-dimensional Convolutional Neural Network (1D CNN) model to predict nutrient profiles, leveraging the typical shape of vertical profiles of a variable as a prior constraint during training. We will present a novel model named PPCon (Predict Profiles Convolutional), which is trained over a dataset containing BCG Argo float measurements, for the prediction of nitrate, chlorophyll and backscattering (bbp700), starting from the date, geolocation, temperature, salinity, and oxygen. The effectiveness of the model is then accurately validated by presenting both quantitative metrics and visual representations of the predicted profiles. Our proposed approach proves capable of overcoming the limitations of MLPs, resulting in smooth and accurate profile predictions.