Recently, Panama wilt disease that attacks banana leaves has caused enormous economic losses to farmers. Early detection of this disease and necessary preventive measures can avoid economic damage. This paper proposes an improved method to predict Panama wilt disease based on symptoms using an agro deep learning algorithm. The proposed deep learning model for detecting Panama wilts disease is essential because it can help accurately identify infected plants in a timely manner. It can be instrumental in large-scale agricultural operations where Panama wilts disease could spread quickly and cause significant crop loss. Additionally, deep learning models can be used to monitor the effectiveness of treatments and help farmers make informed decisions about how to manage the disease best. This method is designed to predict the severity of the disease and its consequences based on the arrangement of color and shape changes in banana leaves. The present proposed method is compared with its previous methods, and it achieved 91.56% accuracy, 91.61% precision, 88.56% recall and 81.56% F1-score.

Eutrophication is the excessive growth of algae in water bodies that causes biodiversity loss, reducing water quality and attractiveness to people. This is an important problem in water bodies. In this paper, we propose a low-cost sensor to monitor eutrophication in concentrations between 0 to 200 mg/L and in different mixtures of sediment and algae (0, 20, 40, 60, 80, and 100% algae, the rest are sediment). We use two light sources (infrared and RGB LED) and two photoreceptors at 90° and 180° of the light sources. The system has a microcontroller (M5stacks) that powers the light sources and obtains the signal received by the photoreceptors. In addition, the microcontroller is responsible for sending information and generating alerts. Our results show that the use of infrared light at 90° can determine the turbidity with an error of 7.45% in NTU readings higher than 2.73 NTUs, and the use of infrared light at 180° can measure the solid concentration with an error of 11.40%. According to the determination of the % of algae, the use of a neural network has a precision of 89.3% in the classification, and the determination of the mg/L of algae in water has an error of 17.95%.

The presence of illicit discharges in sewerage systems generates an important impact in wastewater treatment plants and the ecosystem. In this paper, we present two prototypes for monitoring the presence of solids in wastewater and to study the effect of the water height. The prototypes are based on color and infrared LEDs and two photosensors located in the prototypes at 0° and 180° degrees. When the photosensor is located at 180°, all color LEDs present a good range of output voltage (approximately 5 V to 0 V) and good R2. However, for the typical concentration of solids in wastewater, the prototypes do not work correctly. When the photosensor is located in the prototypes the LEDs, yellow, red, and white have a good operation with voltage differences of 1.73 V, 1.76 V, and 1.13 V in P1 and 1.58 V, 1.84 V, and 1.35 V in P2, respectively. We calculate the mathematical model with the heights and solid concentration. The mathematical models which do not consider height present good R2. In conclusion, when the photosensor is located in the prototype, the height does not have an important effect and can detect the illicit discharge of solids. When the photosensor is located at 180°, it can be used for water with important changes in solid concentrations.

Uncontrolled dumping linked to agricultural vehicles causes an increase in the incorporation of oils into the irrigation system. In this paper, we propose a system based on an optical sensor to monitor oil concentration in the irrigation ditches. Our prototype is based on the absorption and dispersion of light. As a light source, we use Light Emitting Diodes (LEDs) with different colours (white, yellow, blue, green, and red) and a photodetector as a sensing element. To test the sensor’s performance, we incorporate industrial oils used by a diesel or gasoline engine, with a concentration from 0 to 0.20 mL_oil/cm². The experiment was carried out at different water column heights, 0 to 20 cm. According to our results, the sensor can differentiate between the presence or absence of diesel engine oil with any LED. For gasoline engine oil, the sensor quantifies its concentration using the red light source; concentrations greater than 0.1 mL_oil/cm² cannot be distinguished. The data gathered using the red LED has an average absolute error of 0.003 mL_oil/cm² (relative error of 15.8%) for the worst case, 15 cm. Finally, the blue LED generates different signals in the photodetector according to the type of oil. We developed an algorithm that combines (i) the white LED, to monitor the presence of oil; (ii) the blue LED, to identify if the oil comes from a gasoline or diesel engine; and (iii) the red LED, to monitor the concentration of oil used by a gasoline engine.

In irrigation ponds, the excess of nutrients can cause eutrophication, a massive growth of microscopic algae. It might cause different problems in the irrigation infrastructure and should be monitored. In this paper, we present a low-cost sensor based on optical absorption in order to determine the concentration of algae in irrigation ponds. The sensor is composed of 5 LEDs with different wavelengths and light-dependent resistances as photoreceptors. Data are gathered for the calibration of the prototype, including two turbidity sources, sediment and algae, including pure samples and mixed samples. Samples were measured at a different concentration from 15 mg/L to 4000 mg/L. Multiple regression models and artificial neural networks, with a training and validation phase, are compared as two alternative methods to classify the tested samples. Our results indicate that using multiple regression models, it is possible to estimate the concentration of alga with an average absolute error of 32.0 mg/L and an average relative error of 11.0%. On the other hand, it is possible to classify up to 100% of the samples in the validation phase with the artificial neural network. Thus, a novel prototype capable of distinguishing turbidity sources and two classification methodologies, which can be adapted to different node features, are proposed for the operation of the developed prototype.

Soil moisture control is crucial to assess irrigation efficiency in green areas and agriculture. In this paper, we propose the design and calibration of a sensor based on inductive coils and electromagnetic fields. The proposed prototypes should meet a series of requirements such as low power consumption, low relative error, and a high voltage difference between the minimum and maximum moisture. We tested different prototypes based on two copper coils divided into two different sets (P1–P15 and NP1–NP4). The prototypes have different characteristics: variations in the number and distribution of spires, existence or absence of casing, and copper wires with a diameter of 0.4 or 0.6 mm. In the first set of experiments carried out in commercial soil, the results showed that the best prototypes were P5, P8, and P9. These prototypes were used in different types of soils, and P8 was selected for the subsequent tests. We carried the second set of experiments using soil from an agricultural field. Based on the data gathered, mathematical models for the calibration of prototypes were obtained and verified. In some cases, two equations were used for different moisture intervals in a single prototype. According to the verification results, NP2 is the best prototype for monitoring the moisture in agricultural lands. It presented a difference in induced voltage of 1.8 V, at 500 kHz, between wet and dry soil with a maximum voltage of 5.12 V. The verification of the calibration determined that the calibration using two mathematical models offers better results, with an average absolute error of 2.1% of moisture.