EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Neuromorphic-Enhanced Smart Agricultural Intelligence: An Explainable AI Framework for Sustainable IoT-Driven Crop Yield Optimization with Green Energy Integration

Akey Sungheetha, Rajesh Sharma R, Sheila Mahapatra

Procedia Computer Science · 2026 · 283 · 5487-5496

DOI: 10.1016/j.procs.2026.06.598 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Procedia Computer Science, 2026. Verfasst von Akey Sungheetha und 2 weiteren Autor:innen. Die Arbeit nennt 98 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This paper presents the Neuromorphic Explainable Sensor-Fused Artificial Intelligence (NESAI) framework, a theoretically constructed computational model integrating spike-based neural dynamics, multi-modal sensor fusion, and layer-wise relevance propagation for precision agriculture. The framework is formulated entirely within theoretical science computing paradigms, wherein all numerical outcomes are derived through mathematical simulation of biological plausibility in spiking neural networks (SNNs) governed by spike-timing-dependent plasticity (STDP) learning rules with potentiation rate A + = 0.01 and depression rate A_ = 0.012. Sensor modalities encompassing soil volumetric water content (12.3-89.7% VWC), nitrogen concentration (12.4-287.6 ppm), photosynthetically active radiation (0-2347 µ mol/m 2 /s), and atmospheric parameters are mathematically fused under optimised weight vector β = [0.347,0.238,0.184,0.231] across a synthetic dataset of 47,832 computational samples spanning an 18-month agronomic cycle. Theoretical evaluation demonstrates yield prediction accuracy of 92.6%, event-driven system power of 5.3 W, decision latency of 47 ms, and water conservation efficiency of 76.8%. STDP synaptic weight convergence to 0.547 ± 0.083 at 15,000 training samples confirms stable temporal feature selectivity. The explainability module assigns 34.7% relevance to soil moisture, enabling simulated farmer adoption improvement from 58.6% to 91.2%, demonstrating the theoretical viability of neuromorphic-XAI integration for sustainable agriculture computing.

Zitieren

APA

Sungheetha, A., R, R. S., & Mahapatra, S. (2026). Neuromorphic-Enhanced Smart Agricultural Intelligence: An Explainable AI Framework for Sustainable IoT-Driven Crop Yield Optimization with Green Energy Integration. Procedia Computer Science, 283, 5487-5496. https://doi.org/10.1016/j.procs.2026.06.598

Vancouver

Sungheetha A, R RS, Mahapatra S. Neuromorphic-Enhanced Smart Agricultural Intelligence: An Explainable AI Framework for Sustainable IoT-Driven Crop Yield Optimization with Green Energy Integration. Procedia Computer Science. 2026;283:5487-5496. doi:10.1016/j.procs.2026.06.598

BibTeX
@article{Sungheetha2026,
  author = {Sungheetha, Akey and R, Rajesh Sharma and Mahapatra, Sheila},
  title = {Neuromorphic-Enhanced Smart Agricultural Intelligence: An Explainable AI Framework for Sustainable IoT-Driven Crop Yield Optimization with Green Energy Integration},
  journal = {Procedia Computer Science},
  year = {2026},
  volume = {283},
  pages = {5487--5496},
  doi = {10.1016/j.procs.2026.06.598}
}
Kostenlos starten →