Although agriculture remains the dominant economic activity in many countries around the world, in recent years this sector has continued to be negatively impacted by climate change leading to food insecurities. This is so because extreme weather conditions induced by climate change are detrimental to most crops and affect the expected quantity of agricultural production. Although there is no way to fully mitigate these natural phenomena, it could be much better if there is information known earlier about the future so that farmers can plan accordingly. Early information sharing about expected crop production may support food insecurity risk reduction. In this regard, this work employs data mining techniques to predict future crop (i.e., Irish potatoes and Maize) harvests using weather and yields historical data for Musanze, a district in Rwanda. The study applies machine learning techniques to predict crop harvests based on weather data and communicate the information about production trends. Weather data and crop yields for Irish potatoes and maize were gathered from various sources. The collected data were analyzed through Random Forest, Polynomial Regression, and Support Vector Regressor. Rainfall and temperature were used as predictors. The models were trained and tested. The results indicate that Random Forest is the best model with root mean square error of 510.8 and 129.9 for potato and maize, respectively, whereas R² was 0.875 and 0.817 for the same crops datasets. The optimum weather conditions for the optimal crop yield were identified for each crop. The results suggests that Random Forest is recommended model for early crop yield prediction. The findings of this study will go a long way to enhance reliance on data for agriculture and climate change related decisions, especially in low-to-middle income countries such as Rwanda.

Landslides fall under natural, unpredictable and most distractive disasters. Hence, early warning systems of such disasters can alert people and save lives. Some of the recent early warning models make use of Internet of Things to monitor the environmental parameters to predict the disasters. Some other models use machine learning techniques (MLT) to analyse rainfall data along with some internal parameters to predict these hazards. The prediction capability of the existing models and systems are limited in terms of their accuracy. In this research paper, two prediction modelling approaches, namely random forest (RF) and logistic regression (LR), are proposed. These approaches use rainfall datasets as well as various other internal and external parameters for landslide prediction and hence improve the accuracy. Moreover, the prediction performance of these approaches is further improved using antecedent cumulative rainfall data. These models are evaluated using the receiver operating characteristics, area under the curve (ROC-AUC) and false negative rate (FNR) to measure the landslide cases that were not reported. When antecedent rainfall data is included in the prediction, both models (RF and LR) performed better with an AUC of 0.995 and 0.997, respectively. The results proved that there is a good correlation between antecedent precipitation and landslide occurrence rather than between one-day rainfall and landslide occurrence. In terms of incorrect predictions, RF and LR improved FNR to 10.58% and 5.77% respectively. It is also noted that among the various internal factors used for prediction, slope angle has the highest impact than other factors. Comparing both the models, LR model’s performance is better in terms of FNR and it could be preferred for landslide prediction and early warning. LR model’s incorrect prediction rate FNR = 9.61% without including antecedent precipitation data and 3.84% including antecedent precipitation data.

The sub-Saharan Africa region continues to experience food insecurity, a consequence of the less productive agricultural sector that has dragged to adapt to the effects of climate change. As the region’s population continues to grow, there is a need to modernize the region’s agricultural sector to meet the increasing food demand. Although extreme atmospheric conditions cannot be entirely mitigated, however, the integration of technologies such as the Internet of things (IoT) and machine learning (ML) can increase the quantity and quality of production from the crop fields. These technologies have the potential to empower agricultural management systems to handle both climatic and farm data in an orchestrated manner, and inform the formulation of effective strategies. This study presents the design and development of a system for predicting crop yields that integrates IoT and ML. The system combines historic and current weather and crop yield data to predict seasonal crop yields. The weather parameters including, rainfall, temperature, humidity and soil moisture are collected by IoT sensors and transmitted to the cloud for crop yield forecasting. The system is used to analyze seasonal yields of Irish-Potato and Maize in Musanze District of Rwanda. Using data over different agricultural seasons, the system achieved favorable predictive accuracy with mean absolute percentage error (MAPE) values of 0.339, 0.309, and 0.177 for two seasons of Irish potatoes and one season of maize, respectively. Such predictive yield systems can reduce food insecurity risks and enhance harvest efficiency by enabling early awareness of crop production, fostering effective strategies shared among decision-makers and stakeholders. While maize and Irish potatoes were the initial case studies, expansion to include other crops and more variables is envisioned.

Coffee leaf diseases are a significant challenge for coffee cultivation. They can reduce yields, impact bean quality, and necessitate costly disease management efforts. Manual monitoring is labor-intensive and time-consuming. This research introduces a pioneering mobile application equipped with global positioning system (GPS)-enabled reporting capabilities for on-site coffee leaf disease detection. The application integrates advanced deep learning (DL) techniques to empower farmers and agronomists with a rapid and accurate tool for identifying and managing coffee plant health. Leveraging the ubiquity of mobile devices, the app enables users to capture high-resolution images of coffee leaves directly in the field. These images are then processed in real-time using a pre-trained DL model optimized for efficient disease classification. Five models, Xception, ResNet50, Inception-v3, VGG16, and DenseNet, were experimented with on the dataset. All models showed promising performance; however, DenseNet proved to have high scores on all four-leaf classes with a training accuracy of 99.57%. The inclusion of GPS functionality allows precise geotagging of each captured image, providing valuable location-specific information. Through extensive experimentation and validation, the app demonstrates impressive accuracy rates in disease classification. The results indicate the potential of this technology to revolutionize coffee farming practices, leading to improved crop yield and overall plant health.

Shallow landslides are among the natural threats causing death and damage. They are mostly triggered by rainfall in mountainous areas where precipitation used to be abundant. The amount of rainfall inducing this natural threat differs from one site to another based on the geographical characteristics of that area. In addition to the rainfall depth, the determination of soil water content in a specific zone has a major contribution to the landslide prediction and early warning systems. Rwanda being a country with hilly terrains, some areas are susceptible to both rainfall and soil water content inducing landslides. But an analytical study of the physical threshold determination of both rainfall and soil water content inducing landslides is lacking. Therefore, this experimental study is conducted to determine the rainfall and soil water content threshold that can be fed in to the landslide early warning system (LEWS) for alert messages using the Internet of Things (IoT) technology. Various experiments have been conducted for the real-time monitoring of slope failure using the toolset composed of a rain gauge, soil moisture sensors, and a rainfall simulating tool. The results obtained show that the threshold for landslide occurrence does not solely correlate with the total rainfall amount (or intensity) or soil moisture, but also influenced by internal (geological, morphological) and environmental factors. Among the sampled sites, the sites covered by forest indicated no sign of slope failure, whereas sites with crops could slip. The experiments revealed that for a specific site, the minimum duration to induce slope failure was 8 hours, 41 minutes with the rainfall intensity of 8 mm/hour, and the soil moisture was above 90% for deeper sensors. These values are used as thresholds for LEWS for that specific site to improve predictions.