Figure 2. Water level staff-gauges A preliminary study was carried out to find out which were the most relevant locations to have sensors installed along the river, from the source to the mouth in the Pangani river, with special emphasis on the riverside villages. Two locations were identified, the first is the bridge at Kikavu chini village and another one is found at the border of Kilimanjaro and Manyara regions, the Kikuletwa bridge. This was done with the help from the Pangani Water Board (PWB) authority, which is responsible to oversee all the aspects of ground and surface water in the area. Apart from the data being need for this research, PWB required a permanent water monitoring system for producing a satisfactory water flow in order to control its behavior. Figure 3. Sensor installation at Kikuletwa bridge Table 1. Sensor sockets configuration. Table 2. Weather station sensors specifications. Figure 4. Plug&Sense! Smart Agriculture PRO with all parts connected Table 3. Weather station sensors specifications. 3.1.3. 4G module Figure 5. Ultrasonic I2CXL- MaxSonar®-MB7040 from Max- Botix™ sensor Figure 6. Echo sounding technique employed to determine initial river level Figure 7. Ultrasound sensor measurement process. Where dz, is the river height at Kikavu bridge, d;, distance from the sensor to the riverbed, and do, is the sensor-read distance or the distance from the sensor to the water surface. The same procedure was was executed at Kikuletwa bridge with the sensors this time being mounted at the height of 400 cm from the surface of water. Initial river depth at Kikuletwa was measured at 130.5cm. Total distance from the sensor to the riverbed at Kikuletwa bridge can now be written as: Figure 13. The dashboard on the virtual machine. Figure 14. Ultrasound data plot for November 2022 at Kikuletwa bridge. 4.2. Rainfall The pluviometer gives three types of readings, rainfall for the current hour in mil- limeters (mm), previous hour (mm/hour) and accumulated rainfall in the last 24 hours (mm/day). The pluviometer has a small bucket of approximately 0.28mm when full. Dur- ing the measuring process, the switch is closed when the bucket is full and then it is emptied afterwards. Some characteristics of rainfall data are shown in table 5 with a corresponding plot (fig. 15) for the whole period since deployment in April. Table 5. Characteristics of rainfall data from one location Table 6. Characteristics of wind-speed data from one location Table 7. Wind direction value identification. 5. Discussion The solution presented in this paper is significant in at least two major respects. First, as pointed out in the introduction, to deploy reliable early warning systems for floods, we need enough and good quality data. Data is the backbone of any ML system, we therefore provide a solution that will ensure high data precision, accuracy, easy accessibility and completeness. Secondly, as rivers are vital resources that support life of both human and animals, this project will help in water management processes in the basin. Decision on
