**4. Conclusions**

The concept of synthesizing CDs (at zero dimension) on an industrial scale requires automation by first being able to predict the possible outcomes based upon the intended experimental factors. Thus, this study has applied tapioca as the material for optimization to achieve the set objective of large scale synthesis by means of prediction through a reliable approach of utilizing design of experiment (DoE) for a response surface methodology (RSM), to optimize a facile and e ffective synthesis process of fluorescent carbon dots from tapioca powder (starch) via hydrothermal synthesis route. The prediction for optimized fluorescent carbon dots synthesis from RSM is in excellent agreemen<sup>t</sup> with artificial neural network prediction by the Levenberg–Marquardt back propagation (LMBP) algorithm in terms of R2, root mean square error and mean absolute error. Positive hidden layer sizes have resulted in the ANN prediction of PLQY of fluorescent carbon dots at 26.25% and RSM predicted value of 27.38% at R<sup>2</sup> values of 0.94 and 0.95, respectively. The best parameters values for the synthesis of carbon dots were at 170 ◦C for 1 h 40 min with solvent ratio of 12 mL and dosage 0.1 g. These optimization and prediction process have produced sustainable, e fficient, and reliable fluorescent carbon dots, which is energy saving in a manageable time, along with a decreased dosage with optimum quality output.

Moreso, to confirm the validity of carbon dots, characterization of surface morphology and particles size carbon dots were conducted with favorable confirmations of the unique characteristics and attributes of synthesized carbon dots by hydrothermal route.

**Author Contributions:** M.Y.P., As the first author; made the Study conception and design (wrote the ANN codes), Acquisition of data and Drafting of manuscript. Z.Z.A., As the corresponding author; contributed in the Study conception and design (RSM analysis), Critical revision major scientific advisor through clinical experience. S.A.R., As a co-author; served as scientific advisor, critically reviewed the study proposal. F.M.Y., As a co-author; contributed in the Analysis and interpretation of data as well as critically reviewed the study proposal. A.S.M.N., As a co-author; contributed in the Analysis and interpretation of data. M.A.I., As a co-author; contributed in the interpretation of data.

**Funding:** The authors would like to thank Universiti Putra Malaysia, Malaysia as this reported research work is funded by the UPM under the GP-IPS/2017/9556800 grant.

**Data Availability Statement:** The [ANN and RSM] data used to support the findings of this study may be released upon application to Zurina Zainal Abidin, who can be contacted at [zurina@upm.edu.my]. This is an ongoing research.

**Conflicts of Interest:** The authors declare that there is no conflict of interest whatsoever regarding the publication of this paper.
