This paper presents a network intrusion detection system (NIDS) for smart agriculture security using artificial neural networks (ANNs). The system aims to detect and classify intrusions in IoT-based smart farming environments. The proposed framework uses radial basis function neural networks (RBFNN) for intrusion detection and classification. To enhance model performance, the authors applied crowd wisdom tree-based machine learning techniques, including Random Forest (RF), AdaBoost (ADA), Extra Trees (ET), LightGBM (LGBM), and XGBoost (XGB), to select relevant features from the datasets. A single-class support vector machine (1-CSVM) was used to detect and remove outliers. The model was evaluated using the NF-Bot-IoT and NF-ToN-IoT datasets, achieving 99.25% accuracy (ACC) and 82.97% Matthews correlation coefficient (MCC) on the NF-Bot-IoT dataset and 90.05% MCC and 96.92% ACC on the NF-ToN-IoT dataset. The model demonstrated excellent performance in overcoming the imbalance of the NF-Bot-IoT dataset. Smart agriculture relies on IoT technologies, including wireless sensors and cloud computing, to improve agricultural production and quality. However, the adoption of IoT in agriculture exposes the smart farming environment to significant cyber threats. The paper highlights the importance of intrusion detection systems (IDS) in ensuring the security of smart agriculture. The proposed NIDS uses a combination of machine learning techniques and ANNs to detect and classify intrusions in IoT-based smart farming environments. The model's performance was evaluated on two datasets, and the results showed that the model achieved high accuracy and MCC scores, indicating its effectiveness in detecting and classifying intrusions. The paper concludes that the proposed NIDS is a promising solution for enhancing the security of smart agriculture environments.This paper presents a network intrusion detection system (NIDS) for smart agriculture security using artificial neural networks (ANNs). The system aims to detect and classify intrusions in IoT-based smart farming environments. The proposed framework uses radial basis function neural networks (RBFNN) for intrusion detection and classification. To enhance model performance, the authors applied crowd wisdom tree-based machine learning techniques, including Random Forest (RF), AdaBoost (ADA), Extra Trees (ET), LightGBM (LGBM), and XGBoost (XGB), to select relevant features from the datasets. A single-class support vector machine (1-CSVM) was used to detect and remove outliers. The model was evaluated using the NF-Bot-IoT and NF-ToN-IoT datasets, achieving 99.25% accuracy (ACC) and 82.97% Matthews correlation coefficient (MCC) on the NF-Bot-IoT dataset and 90.05% MCC and 96.92% ACC on the NF-ToN-IoT dataset. The model demonstrated excellent performance in overcoming the imbalance of the NF-Bot-IoT dataset. Smart agriculture relies on IoT technologies, including wireless sensors and cloud computing, to improve agricultural production and quality. However, the adoption of IoT in agriculture exposes the smart farming environment to significant cyber threats. The paper highlights the importance of intrusion detection systems (IDS) in ensuring the security of smart agriculture. The proposed NIDS uses a combination of machine learning techniques and ANNs to detect and classify intrusions in IoT-based smart farming environments. The model's performance was evaluated on two datasets, and the results showed that the model achieved high accuracy and MCC scores, indicating its effectiveness in detecting and classifying intrusions. The paper concludes that the proposed NIDS is a promising solution for enhancing the security of smart agriculture environments.