Prediction of breeding regions for the desert locust Schistocerca gregaria in East Africa

Abstract

Desert locust outbreak in East Africa is threatening livelihoods, food security, environment, and economic development in the region. The current magnitude of the desert locust invasion in East Africa is unprecedented and has not been witnessed for more than 70 years. Identifying the potential breeding sites of the pest is essential to carry out cost-effective and timely preventive measures before it inflicts significant damage. We accessed 9,134 desert locust occurrence records and applied a machine-learning algorithm to predict potential desert locust breeding sites in East Africa using key bio-climatic (temperature and rainfall) and edaphic (sand and moisture contents) factors. Ten days greenness maps from February 2020 to April 2020 were overlaid in model outputs to illustrate the temporal evolution of breeding site locations. This study demonstrated that vast areas of Kenya and Sudan, north eastern regions of Uganda, and south eastern and northern regions of South Sudan are at high risk of providing a conducive breeding environment for the desert locust. Our prediction results suggest that there is need to target these high-risk areas and strengthen ground surveillance to manage the pest in a timely, cost-effective, and environmentally friendly manner.

Figure 1

Area under curve for (A) Morocco, (B) Mauritania, and Saudi Arabia (C) models for evaluating the performance of predicting desert locust breeding sites. Zero values for AUC indicate an impossible occurrence area, while values of 1 indicate optimal occurrence area.

Figure 2

Histogram and normal distribution fit for (A) Morocco model, (B) Mauritania model projected from Morocco, and (C) Saudi Arabia model projected from Morocco.

Figure 3

(A) Graphical representation of the ecological niche model for breeding sites of desert locusts in Morocco obtained from MaxEnt with Morocco presence records. (B) Projected model for Mauritania from Morocco model. (C) Projected model for Saudi Arabia from Morocco model. Warmer colors (red) show areas with better-predicted conditions and the green dots indicate the presence locations used for validating the projected models. The figure was generated using the QGIS 3.10.2 software (https://qgis.org/downloads/).

Figure 4

Jackknife of regularized training for Morocco model of desert locusts breeding sites projected to East Africa. Temperature and soil moisture have the highest gain when used in isolation.

Figure 5

A graphical representation of the projected model for desert locust breeding sites in Kenya (A), Uganda (B), South Sudan (C), and Sudan (D) from Morocco model .The dots found in Sudan (647) and Kenya (28) are historical (from 2013 to 2019) and actual (2020) records, respectively, used for measuring the developed model performance. The figure was generated using the QGIS 3.10.2 software (https://qgis.org/downloads/).

Figure 6

Overlaid layer of desert locust habitat suitability area (> 0.6 probability) with the greenness index from February–April 2020: (A) Kenya, (B) Uganda, (C) South Sudan, and (D) Sudan. Values ranging from 1–3 shaded in red indicate the areas with on-set of vegetation favorable for desert locust. Point locations with green vegetation that overlap with models’ outputs are actual desert locust highly suitable breeding areas.The figure was generated using the QGIS 3.10.2 software (https://qgis.org/downloads/).

Figure 7

Temporal vegetation change from 1st Feb to 10th April (left to right) showing areas with on-set of vegetation favorable for desert locust breeding. These maps have shown that the potential location of desert locust breeding sites evolves with time in a predicted area in Kenya. The figure was generated using the QGIS 3.10.2 software (https://qgis.org/downloads/).

Figure 8

(A) Desert locust breeding sites collected in Africa, the Middle East, and Western Asia from 1985 to 2020. The brown dots are the records used for developing and validating the model; the green dots represent the breeding sites used for measuring the model performance, while the black dots are known breeding sites for desert locust. (B) Heat map indicating the hotspot areas where the majority of desert locust nymph presence records were collected from 1985 to 2020 in Mauritania, Morocco, and Saudi Arabia. High intensity of desert locust nymph presence is characterized by red color, while the blue color displays a low repetitive occurrence in the same point location of desert locust nymph. The figure was generated using the QGIS 3.10.2 software (https://qgis.org/downloads/).