Ecogeoguard: A Dual Approach to Environmental Safety and Crop Yield
DOI:
https://doi.org/10.63503/acset.978-81-995593-9-4.53Keywords:
Landslide prediction, smart agriculture, livestock tracking, disaster management, climate resilience, early warning systems, artificial intelligence, rural sustainabilityAbstract
A community-focused AI-IoT technology, EcoGeoGuard combines livestock safety tracking, precision agriculture analytics, and multi-sensor geophysical monitoring into a single real-time intelligence ecosystem. In addition to GPS-enabled livestock trackers, the system uses inexpensive environmental sensors, such as MEMS accelerometers, geophones, tilt sensors, soil-moisture probes, and BME280 weather modules, all connected via a hybrid LoRa/NB-IoT/Wi-Fi communication architecture. Before being fed into a cloud-based analytics pipeline via AWS IoT Core, data is processed at the edge using FFT-based vibration analysis and threshold filtering. Machine learning algorithms, such as Random Forests, Gradient Boosting, Linear Regression, and K-Means clustering, are used to analyse time-series streams to identify early warning signs of slope instability, optimise the use of irrigation and fertilisers, and detect cow movements outside designated safety zones. The anomaly management layer calculates risk ratings and activates multi-channel alerts via dashboards, SMS, mobile applications, and local siren units. EcoGeoGuard is a holistic early-warning and decision-support platform to safeguard livestock and population in disaster-prone regions, enhance productive rural agriculture, and enhance climate resilience. It includes network resilience and energy-efficient, solar-powered nodes.
References
[1] H. R. Najafabadi, A. Jafari, and L. Rahman, Designing MEMS accelerometer for enhanced sensitivity and reduced cross-sensitivity in landslide monitoring. Measurement, 2024. 226: p. 114092–114099.
[2] L. Badru, J. Namaganda, and F. Okello, An IoT-Based Landslide Detection and Early Warning System in Hilly Areas. East African Journal of Information Technology, 2022. 5(1): p. 31–38.
[3] A. Wicki, P. Baumann, and D. Rickli, Assessing the potential of soil moisture measurements for regional landslide early warning. Landslides, 2020. 17(8): p. 1881–1896.
[4] S. K. Mittal, V. K. Sharma, and A. Agarwal, Design and development of an instrumentation network for landslide monitoring and the issue of early warning. Journal of Scientific and Industrial Research, 2008. 67(5): p. 361–366.
[5] G. Shanmugavadivel, P. Sivaranjani, and K. Sharmila, Detecting Communication Network Anomalies and Intrusions Using Hybrid Deep Learning. in Proc. 6th Int. Conf. Intelligent Computing and Control Systems (ICICCS). 2022. IEEE. p. 415–422.
[6] R. M. Devi, P. Anitha, and S. Jayanthi, Design of intelligent IoT for smart environmental and weather monitoring using optimal machine learning methods. International Journal of Health Sciences, 2022. 6(2): p. 13422–13434.
[7] A. Dikshit, D. N. Satyam, and I. Towhata, Early warning system using tilt sensors in Chibo, Kalimpong, Darjeeling Himalayas, India. Natural Hazards, 2018. 94(2): p. 727–741.
[8] R. Binali, M. H. T. Al-Khulaifi, and Y. Song, A Comprehensive Review on Low-Cost MEMS Accelerometers for Vibration Measurement. Journal of Molecular Engineering Materials, 2024. 12(3): p. 240–252.
[9] P. Kumar, R. Mehta, and A. Banerjee, AI-Based Climate Adaptive Farming Systems for Indian Agriculture. IEEE Access, 2023. 11: p. 49205–49218.
[10] M. Gupta, S. Sen, and P. Raj, Smart Agriculture and Climate Prediction using IoT and Machine Learning. Procedia Computer Science, 2023. 218: p. 1458–1467.
[11] T. Setiawan and R. Y. Cysela, Landslide Monitoring Using Inclinometer with MEMS Technology, in IOP Conf. Ser.: Earth and Environmental Science. 2021. 873: p. 012017.
[12] S. Mittal and D. Gupta, IoT and Edge Computing for Climate-Resilient Smart Villages: A Case Study of Rural India. Sustainability, 2023. 15(6): p. 5229–5241
[13] M. S. Bhatia and K. Nair, Integration of IoT and AI for Disaster Management and Early Warning Systems. International Journal of Advanced Computer Science and Applications, 2022. 13(8): p. 88–96.
[14] C. Jing, H. Zhang, and X. Chen, GNSS/Accelerometer Coupled Landslide Deformation Monitoring Technology. Remote Sensing, 2022. 14(15): p. 3537–3545.
[15] S. Vimalnath, K. Madhumitha, and A. Kirubasakthi, Next-Generation Environmental Monitoring Using IoT. In Proc. 2nd Int. Conf. Artificial Intelligence and Machine Learning Applications (AIMLA). 2024. IEEE. p. 210–216.
[16] A. Pradhan, S. Chowdhury, and K. Das, LoRa-Based Wireless Sensor Network for Remote Environmental Monitoring in Hilly Terrains. IEEE Sensors Journal, 2023. 23(4): p. 5121–5130.
[17] B. Pathak, N. Ray, and M. Kar, Machine Learning-Based Prediction of Rainfall-Induced Landslides Using Sensor and Weather Data. Natural Hazards, 2024. 117: p. 297–317.
[18] Y. Yuan, C. Liu, and J. Ma, Edge-Cloud Collaborative Computing for IoT-Based Hazard Warning Systems. IEEE Internet of Things Journal, 2023. 10(2): p. 1348–1360.
[19] N. Sharma and R. Gautam, Development of Soil-Moisture Monitoring System for Precision Irrigation Using IoT. Journal of Agricultural Engineering, 2023. 60(1): p. 89–98.
[20] H. Li, Z. Wang, and Q. Chen, Weather Prediction Models Using Pressure and Humidity Trends: A Machine Learning Perspective. Applied Computational Intelligence and Soft Computing, 2022. p. 1–12.
[21] K. Singh, A. Verma, and P. Kaur, Design of Low-Cost Tilt Monitoring System for Geological Hazard Detection. Measurement Science Review, 2023. 23: p. 149–158.
[22] M. Alam and F. Hussain, A Hybrid LoRa–NB-IoT Communication Model for Real-Time Rural IoT Systems. International Journal of Distributed Sensor Networks, 2023. 19(5): p. 1–14.
[23] P. Rana, S. Tamang, and D. S. Jha, Geophone-Based Early Detection of Landslide Vibration Signatures in Himalayan Regions. Geotechnical & Geological Engineering, 2023. 41: p. 4251–4267.
[24] L. Torres and M. Estrada, IoT-Based Livestock Tracking and Geo-Fencing Using GPS and LoRaWAN. Computers and Electronics in Agriculture, 2023. 210: p. 107911–107923.
[25] T. Nguyen and R. Chandrasekar, Smart Farming Through IoT and AI: A Review of Sensor Integration, Data Analytics, and Predictive Models. Computers & Electrical Engineering, 2024. 112: p. 108840–108858.
[26] F. Carpentieri and D. O’Neill, Multisensor Fusion for Land Deformation Monitoring Using Inclinometers and MEMS Sensors. Sensors, 2023. 23(8): p. 4021–4032.
[27] J. Patel, A. Saxena, and M. Jain, Cloud-Based IoT Architecture for Environmental Monitoring Using MQTT Protocol. International Journal of Cloud Applications and Computing, 2023. 13(2): p. 52–65.
