Optimization of hybrid green extraction techniques for bioactive compounds from citrus lemon peel using response surface methodology (RSM) and artificial neural network (ANN)

Lemon peels are not just waste—they're a treasure trove of antioxidants. But old extraction methods are slow and solvent-hungry. What if we could unlock their power faster, greener, and smarter?

Citrus limon peel, a byproduct of the citrus industry, is packed with polyphenols, flavonoids, and antioxidants. Yet conventional extraction methods drag on, consuming excess solvents and time. Scientists are now turning to hybrid green techniques—microwave pretreatment followed by ultrasound-assisted extraction—to pull out these bioactives efficiently.

In a new study, researchers compared two modeling approaches: Response Surface Methodology (RSM) and Artificial Neural Network (ANN). Both models captured the interplay between processing parameters and yields. Surprisingly, RSM outperformed ANN in prediction accuracy for this dataset, though both performed well.

The optimized conditions—microwave power of 516.74 W for 101.86 seconds, then ultrasound at 40°C for 21.033 minutes—yielded impressive results: 2283.72 mg GAE/100 g of total phenolic content, 987.58 mg QE/100 g of flavonoids, and 78.21% DPPH scavenging activity, with a desirability score of 0.99.

Beyond efficiency, this approach slashed energy consumption by 23.42% compared to ultrasound alone, cutting CO2 emissions too. It's a win for both industry and the planet—a scalable, green method to valorize lemon peel waste.

Key Points

• RSM beats ANN in prediction accuracy for this dataset.
• Optimized conditions yield high TPC, TFC, and antioxidant activity.
• Energy consumption cut by 23.42% versus ultrasound alone.