Agroecological farming systems such as maize–legume intercropping (MLI) and push-pull technology (PPT) have been introduced to mitigate losses from pests. Nevertheless, the regionwide maize yield gained from practicing such farming systems remains largely unknown. This study compares the performance of two uncomplex and interpretable models, namely the hybrid fuzzy-logic combined with the genetic algorithm and symbolic regression, to predict maize yield. Specifically, the study adopted the best-fitting model to map the potential maize yield under MLI and PPT compared to the monocropping system in East Africa using climatic and edaphic variables. The best model, i.e., the symbolic regression model, accurately fitted the maize yield data as indicated by the low root mean square error (RMSE < 0.09) and the higher R² (>0.9). The study estimated that East African farmers would increase their annual maize yield by about 1.01 and 1.96 rates under MLI and PPT, respectively. Furthermore, the results showed a fairly good modelling performance as indicated by low standard deviations (range of 0.70–1.1) and skewness (absolute range of 0.03–0.09) values. The study guides the upscaling of MLI and PPT systems through awareness creation and public-private partnerships to ensure increased adoption of these sustainable farming practices.

The South American tomato pinworm, Tuta absoluta, causes up to 100% tomato crop losses. As Tuta absoluta is non-native to African agroecologies and lacks efficient resident natural enemies, the microgastrine koinobiont solitary oligophagous larval endoparasitoid, Dolichogenidea gelechiidivoris (Marsh) (Syn.: Apanteles gelechiidivoris Marsh) (Hymenoptera: Braconidae) was released for classical biological control. This study elucidates the current and future spatio-temporal performance of D. gelechiidivoris against T. absoluta in tomato cropping systems using a fuzzy logic modelling approach. Specifically, the study considers the presence of the host and the host crop, as well as the parasitoid reproductive capacity, as key variables. Results show that the fuzzy algorithm predicted the performance of the parasitoid (in terms of net reproductive rate (R₀)), with a low root mean square error (RMSE) value (<0.90) and a considerably high R² coefficient (=0.98), accurately predicting the parasitoid performance over time and space. Under the current climatic scenario, the parasitoid is predicted to perform well in all regions throughout the year, except for the coastal region. Under the future climatic scenario, the performance of the parasitoid is projected to improve in all regions throughout the year. Overall, the model sheds light on the varying performance of the parasitoid across different regions of Kenya, and in different seasons, under both current and future climatic scenarios.

Classical biological control (CBC) has been exploited as a safer alternative for suppressing the oriental fruit fly, Bactrocera dorsalis, by importing, rearing, and releasing the larval parasitoid, Diachasmimorpha longicaudata. Although D. longicaudata has been released in Kenya through the Africa Fruit Fly Programme, the extent of its dispersal and subsequent economic benefits have not yet been established. This paper models the spatio-temporal dispersal of the parasitoid using the fuzzy cellular automata approaches and estimates the net benefit from each dollar invested in the CBC approach. We calculated the return on investment based on funding into the programme between 2006 and 2015 and the result of the dispersal range of the parasitoid predicted using an artificial intelligence algorithm. The investment yielded a significant net present value of US$42.8 million over the 16 years. Besides, the cost–benefit ratio showed that for every US$1 invested, the return benefit was US$93, confirming the profitability of the CBC program. The economic gains are significant considering that there is no environmental contamination and possible adverse effects from the CBC intervention. The study findings support investment in biological control strategies for the eco-friendly and area-wide management of B. dorsalis.

This study introduces a hybrid approach that combines unsupervised self-organizing maps (SOM) with a supervised convolutional neural network (CNN) to enhance model accuracy in vector-borne disease modeling. We applied this method to predict insecticide resistance (IR) status in key malaria vectors across Africa. Our results show that the combined SOM/CNN approach is more robust than a standalone CNN model, achieving higher overall accuracy and Kappa scores among others. This confirms the potential of the SOM/CNN hybrid as an effective and reliable tool for improving model accuracy in public health applications.•The hybrid model, combining SOM and CNN, was implemented to predict IR status in malaria vectors, providing enhanced accuracy across various validation metrics.•Results indicate a notable improvement in robustness and predictive accuracy over traditional CNN models.•The combined SOM/CNN approach demonstrated higher Kappa scores and overall model accuracy.