Umberto Garlando

This study explores time series anomaly detection using a long short-term memory (LSTM) neural network to identify abnormal plant conditions—both biotic and abiotic—by analyzing a stem frequency parameter. This parameter, closely linked to plant stem conductivity, serves as a novel indicator of plant hydration and overall physiological status. Four independent experiments were conducted between 28 May 2024, and 16 December 2024, and 20 tomato plants were maintained under different conditions (healthy, biotic, and abiotic stress) to assess physiological differences and develop models for early symptom detection. We used samples from healthy plants to train an LSTM neural network to predict stem frequency values 24 h ahead. The trained model was then used to forecast the behavior of stressed plants, and an anomaly was flagged whenever the predicted values significantly deviated from the measured ones. Our LSTM-based anomaly detection model successfully detected water stress conditions several days before visible symptoms appeared. However, the algorithm struggled to distinguish early signs of Fusarium infection. Despite this limitation, in most cases, the model provided early warnings of biotic stress before any visual symptoms were evident. Future research will focus on expanding the dataset to enhance the model’s ability to differentiate between various types of plant stress. This article builds upon the work presented at CAFE 2024 Cum et al., 2024, utilizing the same experimental setup but exploring a completely different approach for the early identification of stress symptoms in tomato plants.

Water is a not-so-renewable resource. Agriculture is impacting for more than 70% of fresh water use worldwide. Considering the increase of population it is fundamental to act in order to reduce water usage. The WAPPFRUIT project aims to design an automatic irrigation system, based on data of water availability in the soil gathered directly in the orchards. Matric potential data are used to determine the exact water demand of the trees, thanks to specific thresholds adapted to the actual soil and crop type. Furthermore, an electronic system based on simple, small, and ultra-low-power devices works together an automatic algorithm to manage the watering events. We tested this approach in three orchards in north-west Italy, comparing our approach to the one used by the farmers. The results show an average water saving of nearly 50% keeping the fruit production comparable to the reference solution. This approach is a clear example of how electronics and technology can really impact agriculture and food production.

Food security, producing enough food for every person on the planet, is becoming a significant issue. Increasing world population and climate change are setting new challenges to food production. Water stress can cause severe damage to crops, and detecting and preventing this threat is crucial. Smart agriculture and the use of sensors directly on the field is a promising and rapidly evolving solution. Data collected by a large number of sensors must be analyzed and efficiently interpreted. In this context, machine learning is an effective solution. This article conducts a comparative analysis of several well-established machine learning models, all trained on a dataset enriched with a novel parameter for the assessment of plant health, the stem electrical impedance (modulus and phase). This feature gives promising results since it is a direct parameter of the plant itself. Moreover, the inclusion of the stem impedance parameter significantly boosted the model's performance, notably enhancing the effectiveness, particularly evident in the case of the top-performing model in this study, the random forest algorithm. When incorporating stem electrical impedance, this model achieved an impressive F1 score of 98%, markedly surpassing the 88% obtained in its absence. As a complementary analysis, a permutation feature performance analysis was conducted, highlighting the potential of stem impedance modulus as a promising feature for evaluating plant watering conditions. The removal of impedance modulus from the training model resulted in an average classification performance loss of 25% in terms of F1 score, suggesting how impedance monitoring is a promising approach for plant health management.

A step forward in smart agriculture is moving to direct monitoring plants and crops instead of their environment. Understanding plant status is crucial in improving food production and reducing the usage of water and chemicals in agriculture. Here, we propose a “plant-wearable,” low-cost, and low-power method to measure in-vivo green plant stem frequency as the indicator for plant watering stress status. Our method is based on measuring the frequency of a digital signal obtained with a relaxation oscillator where the plant is a part of the feedback loop. The frequency was correlated with the soil water potential, used as a critical indicator of plant water stress, and an 85% correlation was found. In this way, the measuring system matches all the requirements of smart agriculture and Internet of Things (IoT): ultra-low-cost, low-complexity, ultra-low-power, and small sizes, introducing the concept of wearability in plant monitoring. The proposed solution exploits the plant and the soil as a communication channel: the signal carrying the plant watering stress status information is transmitted to a receiving system connected to a different plant. The system's current consumption is lower than 50 $\bm {\mu }$ A during the transmission in the plant and 40 mA for wireless communication. During inactivity periods, the total current consumption is lower than 15 $\bm {\mu }$ A. Another important aspect is that the system has to be energy autonomous. Our proposal is based on energy harvesting solutions from multiple sources: solar cells and plant microbial fuel cells. This way, the system is batteryless, thanks to supercapacitors as a storage element. The system can be deployed in the fields and used to monitor plants directly in their environment.

In CMOS-based electronics, the most straightforward way to implement a summation operation is to use the ripple carry adder (RCA). Magnonics, the field of science concerned with data processing by spin waves and their quanta magnons, recently proposed a magnonic half-adder that can be considered as the simplest magnonic integrated circuit. Here, we develop a computation model for the magnonic basic blocks to enable the design and simulation of magnonic gates and magnonic circuits of arbitrary complexity and demonstrate its functionality on the example of a 32-bit integrated RCA. It is shown that the RCA requires the utilization of additional regenerators based on magnonic directional couplers with embedded amplifiers to normalize the magnon signals in-between the half-adders. The benchmarking of large-scale magnonic integrated circuits is performed. The energy consumption of 30 nm-based magnonic 32-bit adder can be as low as 961 aJ per operation with taking into account all required amplifiers.

Molecular Field-Coupling Nanocomputing (FCN) is one of the most promising technologies for overcoming Complementary Metal Oxide Semiconductor (CMOS) scaling issues. It encodes the information in the charge distribution of nanometric molecules and propagates it through local electrostatic intermolecular interaction. This technology promises very high speed at ambient temperatures with minimal power dissipation. The main research focus on molecular FCN is currently either on single-molecule low-level analysis or circuit design based on naïve assumptions. We aim to fill this gap, assessing the potential and feasibility of FCN. We present a bottom-up analysis and design framework that starts from the physical characterization of molecular and technological parameters and enables physical-aware FCN designs. The framework explicitly considers molecular physics, allowing the designer to tame the molecular interaction to ensure the computational capabilities of the final device. The framework permits studying possible physical effects that create cross-implications and correlations among physical and system-level layers considering possible behavior variability. We characterize and verify molecular propagation in increasingly structured layouts to design complex arithmetic circuits. The results highlight molecular FCN advantages, especially in area occupation, and provide valuable quantitative feedback to designers and technologists to support the assessment of molecular FCN and the realization of an eventual prototype.

Many beyond-CMOS technologies, based on different switching mechanisms, are arising. Field-coupled technologies are the most promising as they can guarantee an extremely low-power consumption and combine logic and memory into the same device. However, circuit-level explorations, like layout verification and analysis of the circuit performance, considering the constraints of the target technology, cannot be done using existing tools. Here, we propose a methodology to take on this challenge. We present FUNCODE (FUNction & COnnection DEtection), an algorithm that can detect element connections, functions and errors of custom-layouts and generate its corresponding VHDL netlist. It is proposed for in-plane and perpendicular Nano Magnetic Logic as a case study. FUNCODE netlists, which take into account the physical behavior of the technology, were verified using circuits with increasing complexity, from 6 up to 1400 gates with a number of layout elements varying from 200 to 2.3e6.