Predicting maximum temperatures over India 10-days ahead using machine learning models.

In the months of March-June, India experiences high daytime temperatures (Tmax), which sometimes lead to heatwave-like conditions over India. In this study, 10 different machine learning models are evaluated for their ability to predict the daily Tmax anomalies 10 days ahead in the months of March-June. Several model experiments were carried out to identify an optimal model to predict daily Tmax anomalies over India. The results indicate that the AdaBoost regressor with Multi-layer Perceptron as the base estimator is an optimal model to predict the Tmax anomalies over India in the months of March-June. The optimal model predictions are benchmarked against 10-day persistence predictions and the predictions from the Climate Forecast System (CFS) reforecast. The results indicate that the machine learning model skill is higher than persistence and comparable to CFS reforecast 10-day predictions in April and May. In March and June, the machine learning models have low skill scores and perform no better than persistence. These results indicate that the machine learning models are promising tools to predict the surface air maximum temperature anomalies over India in April and May and can complement predictions from more sophisticated numerical models.

Utilizing a novel high-resolution malaria dataset for climate-informed predictions with a deep learning transformer model.

Climatic factors influence malaria transmission via the effect on the Anopheles vector and Plasmodium parasite. Modelling and understanding the complex effects that climate has on malaria incidence can enable important early warning capabilities. Deep learning applications across fields are proving valuable, however the field of epidemiological forecasting is still in its infancy with a lack of applied deep learning studies for malaria in southern Africa which leverage quality datasets. Using a novel high resolution malaria incidence dataset containing 23 years of daily data from 1998 to 2021, a statistical model and XGBOOST machine learning model were compared to a deep learning Transformer model by assessing the accuracy of their numerical predictions. A novel loss function, used to account for the variable nature of the data yielded performance around + 20% compared to the standard MSE loss. When numerical predictions were converted to alert thresholds to mimic use in a real-world setting, the Transformer's performance of 80% according to AUROC was 20-40% higher than the statistical and XGBOOST models and it had the highest overall accuracy of 98%. The Transformer performed consistently with increased accuracy as more climate variables were used, indicating further potential for this prediction framework to predict malaria incidence at a daily level using climate data for southern Africa.

An urgent need for COP27: confronting converging crises.

The last 12 months have provided further evidence of the potential for cascading ecological and socio-political crises that were warned of 12 months ago. Then a consensus statement from the Regional Action on Climate Change Symposium warned: "the Earth's climatic, ecological, and human systems are converging towards a crisis that threatens to engulf global civilization within the lifetimes of children now living." Since then, the consequences of a broad set of extreme climate events (notably droughts, floods, and fires) have been compounded by interaction with impacts from multiple pandemics (including COVID-19 and cholera) and the Russia-Ukraine war. As a result, new connections are becoming visible between climate change and human health, large vulnerable populations are experiencing food crises, climate refugees are on the move, and the risks of water, food, and climate disruption have been visibly converging and compounding. Many vulnerable populations now face serious challenges to adapt. In light of these trends, this year, RACC identifies a range of measures to be taken at global and regional levels to bolster the resilience of these populations in the face of such emerging crises. In particular, at all scales, there is a need for globally available local data, reliable analytic techniques, community capacity to plan adaptation strategies, and the resources (scientific, technical, cultural, and economic) to implement them. To date, the rate of growth of the support for climate change resilience lags behind the rapid growth of cascading and converging risks. As an urgent message to COP27, it is proposed that the time is now right to devote much greater emphasis, global funding, and support to the increasing adaptation needs of vulnerable populations.

Predicting malaria outbreaks from sea surface temperature variability up to 9 months ahead in Limpopo, South Africa, using machine learning.

Malaria is the cause of nearly half a million deaths worldwide each year, posing a great socioeconomic burden. Despite recent progress in understanding the influence of climate on malaria infection rates, climatic sources of predictability remain poorly understood and underexploited. Local weather variability alone provides predictive power at short lead times of 1-2 months, too short to adequately plan intervention measures. Here, we show that tropical climatic variability and associated sea surface temperature over the Pacific and Indian Oceans are valuable for predicting malaria in Limpopo, South Africa, up to three seasons ahead. Climatic precursors of malaria outbreaks are first identified via lag-regression analysis of climate data obtained from reanalysis and observational datasets with respect to the monthly malaria case count data provided from 1998-2020 by the Malaria Institute in Tzaneen, South Africa. Out of 11 sea surface temperature sectors analyzed, two regions, the Indian Ocean and western Pacific Ocean regions, emerge as the most robust precursors. The predictive value of these precursors is demonstrated by training a suite of machine-learning classification models to predict whether malaria case counts are above or below the median historical levels and assessing their skills in providing early warning predictions of malaria incidence with lead times ranging from 1 month to a year. Through the development of this prediction system, we find that past information about SST over the western Pacific Ocean offers impressive prediction skills (~80% accuracy) for up to three seasons (9 months) ahead. SST variability over the tropical Indian Ocean is also found to provide good skills up to two seasons (6 months) ahead. This outcome represents an extension of the effective prediction lead time by about one to two seasons compared to previous prediction systems that were more computationally costly compared to the machine learning techniques used in the current study. It also demonstrates the value of climatic information and the prediction framework developed herein for the early planning of interventions against malaria outbreaks.

Global wave number-4 pattern in the southern subtropical sea surface temperature.

Exploratory analysis using empirical orthogonal function revealed the presence of a stationary zonal wavenumber-4 (W4) pattern in the sea surface temperature (SST) anomaly in the southern subtropics (20°S-55°S). The signal over the Southern subtropics is seasonally phase-locked to the austral summer and persists up to mid-autumn. Thermodynamic coupling of atmosphere and the upper ocean helps in generating the W4 pattern, which later terminates due to the breaking of that coupled feedback. It is found that the presence of anomalous SST due to W4 mode in the surrounding of Australia affects the rainfall over the continent by modulating the local atmospheric circulation. During positive phase of W4 event, the presence of cold SST anomaly over the south-eastern and -western side of Australia creates an anomalous divergence circulation. This favours the moisture transport towards south-eastern Australia, resulting in more rainfall in February. The scenario reverses in case of a negative W4 event. There is also a difference of one month between the occurrence of positive and negative W4 peaks. This asymmetry seems to be responsible for the weak SST signal to the South of Australia. Correlation analysis suggests that the W4 pattern in SST is independent of other natural variabilities such as Southern Annular Mode, and Indian Ocean Dipole as well as a rather weak relationship with El Niño/Southern Oscillation.

Summertime sea-ice prediction in the Weddell Sea improved by sea-ice thickness initialization.

Skillful sea-ice prediction in the Antarctic Ocean remains a big challenge due to paucity of sea-ice observations and insufficient representation of sea-ice processes in climate models. Using a coupled general circulation model, this study demonstrates skillful prediction of the summertime sea-ice concentration (SIC) in the Weddell Sea with wintertime SIC and sea-ice thickness (SIT) initializations. During low sea-ice years of the Weddell Sea, negative SIT anomalies initialized in June retain the memory throughout austral winter owing to horizontal advection of the SIT anomalies. The SIT anomalies continue to develop in austral spring owing to more incoming solar radiation and the associated warming of mixed layer, contributing to further sea-ice decrease during late austral summer-early autumn. Concomitantly, the model reasonably reproduces atmospheric circulation anomalies during austral spring in the Amundsen-Bellingshausen Seas besides the Weddell Sea. These results provide evidence that the wintertime SIT initialization benefits skillful summertime sea-ice prediction in the Antarctic Seas.

A machine learning based prediction system for the Indian Ocean Dipole.

The Indian Ocean Dipole (IOD) is a mode of climate variability observed in the Indian Ocean sea surface temperature anomalies with one pole off Sumatra and the other pole near East Africa. An IOD event starts sometime in May-June, peaks in September-October and ends in November. Through atmospheric teleconnections, it affects the climate of many parts of the world, especially that of East Africa, Australia, India, Japan, and Europe. Owing to its large impacts, previous studies have addressed the predictability of the IOD using state of the art coupled climate models. Here, for the first-time, we predict the IOD using machine learning techniques, in particular artificial neural networks (ANNs). The IOD forecasts are generated for May to November from February-April conditions. The attributes for the ANNs are derived from sea surface temperature, 850 hPa and 200 hPa geopotential height anomalies, using a correlation analysis for the period 1949-2018. An ensemble of ANN forecasts is generated using 500 samples with replacement using jackknife approach. The ensemble mean of the IOD forecasts indicates the machine learning based ANN models to be capable of forecasting the IOD index well in advance with excellent skills. The forecast skills are much superior to the skills obtained from the persistence forecasts that one would guess from the observed data. The ANN models also perform far better than the models of the North American Multi-Model Ensemble (NMME) with higher correlation coefficients and lower root mean square errors (RMSE) for all the target months of May-November.

Long-lead Prediction of ENSO Modoki Index using Machine Learning algorithms.

The focus of this study is to evaluate the efficacy of Machine Learning (ML) algorithms in the long-lead prediction of El Niño (La Niña) Modoki (ENSO Modoki) index (EMI). We evaluated two widely used non-linear ML algorithms namely Support Vector Regression (SVR) and Random Forest (RF) to forecast the EMI at various lead times, viz. 6, 12, 18 and 24 months. The predictors for the EMI are identified using Kendall's tau correlation coefficient between the monthly EMI index and the monthly anomalies of the slowly varying climate variables such as sea surface temperature (SST), sea surface height (SSH) and soil moisture content (SMC). The importance of each of the predictors is evaluated using the Supervised Principal Component Analysis (SPCA). The results indicate both SVR and RF to be capable of forecasting the phase of the EMI realistically at both 6-months and 12-months lead times though the amplitude of the EMI is underestimated for the strong events. The analysis also indicates the SVR to perform better than the RF method in forecasting the EMI.

Why apple orchards are shifting to the higher altitudes of the Himalayas?

Apple cultivation is one of the most important sources of livelihood in Indian side of the Himalayas. The present study focuses on the apple orchards of Himachal Pradesh, a state within the Himalayan Mountains, a major apple producers of India. In the study, it is found that the optimum apple growing conditions in the region have been consistently shifting and farmers are shifting their orchards to the higher altitudes. For example, orchards have shifted to 1500-2500 meters in the 2000s compared to the cultivated elevation of 1200-1500 meters during 1980s. As of 2014, apples are being cultivated at an elevation of more than 3500 meters, for example, the newly developed orchards of Leo village in upper Kinnaur and Keylong area of Lahul and Spiti districts. Chilling hours for different districts are calculated. The trend of temperature during the growth period, winter session and annual rainfall have been analysed using Mann-Kendall and Sen's slope test. Data catalogued from different time periods indicates that the northward shift (towards higher altitude) is due to changes in chilling hours, total annual rainfall and mean surface temperature during the apple growing season. The mean surface temperature in all the districts has increased by almost 0.5°C during last 2000-2014. These changes are directly related to global warming. While the changing climate is reducing the apple production in low altitudinal regions of the state, it is creating new opportunities for apple cultivation in higher altitudes as conditions are getting more favourable for apple growth in those higher regions. The associated socio-economic changes are posing new societal issues for the local farmers.

Role of sea-ice initialization in climate predictability over the Weddell Sea.

Potential impact of sea-ice initialization on the interannual climate predictability over the Weddell Sea is investigated using a coupled general circulation model. Climate variability in the Weddell Sea is generally believed to have association with remote forcing such as El Niño-Southern Oscillation and the Southern Annual Mode. However, sea-ice variability in the Weddell Sea has been recently suggested to play additional roles in modulating local atmospheric variability through changes in surface air temperature and near-surface baroclinicity. Reforecast experiments from September 1st, in which the model's sea-surface temperature (SST) and sea-ice concentration (SIC) are initialized with observations using nudging schemes, show improvements in predicting the observed SIC anomalies in the Weddell Sea up to four months ahead, compared to the other experiments in which only the model's SST is initialized. During austral spring (Oct-Dec) of lower-than-normal sea-ice years in the Weddell Sea, reforecast experiments with the SST and SIC initializations reasonably predict high surface air temperature anomalies in the Weddell Sea and high sea-level pressure anomalies over the Atlantic sector of the Southern Ocean. These results suggest that accurate initialization of sea-ice conditions during austral winter is necessary for skillful prediction of climate variability over the Weddell Sea during austral spring.

Improving seasonal forecasts of air temperature using a genetic algorithm.

Seasonal forecasts of air-temperature generated by numerical models provide guidance to the planners and to the society as a whole. However, generating accurate seasonal forecasts is challenging mainly due to the stochastic nature of the atmospheric internal variability. Therefore, an array of ensemble members is often used to capture the prediction signals. With large spread in the prediction plumes, it becomes important to employ techniques to reduce the effects of unrealistic members. One such technique is to create a weighted average of the ensemble members of seasonal forecasts. In this study, we applied a machine learning technique, viz. a genetic algorithm, to derive optimum weights for the 24-ensemble members of the coupled general circulation model; the Scale Interaction Experiment-Frontier research center for global change version 2 (SINTEX-F2) boreal summer forecasts. Our analysis showed the technique to have significantly improved the 2m-air temperature anomalies over several regions of South America, North America, Australia and Russia compared to the unweighted ensemble mean. The spatial distribution of air temperature anomalies is improved by the GA technique leading to better representation of anomalies in the predictions. Hence, machine learning techniques could help in improving the regional air temperature forecasts over the mid- and high-latitude regions where the model skills are relatively modest.

Quasi-asymmetric response of the Indian summer monsoon rainfall to opposite phases of the IOD.

The El Niño/Southern Oscillation has been traditionally linked to the extremes in the Indian summer monsoon rainfall (ISMR) affecting more than a billion people in the region. This trans-oceanic influence is seen to be moderated by the Indian Ocean Dipole (IOD) phenomenon in recent decades. In the presence of a positive IOD (pIOD), the otherwise subdued ISMR in an El Niño year remains close to normal even in the face of record breaking El Niños. While this general influence of pIOD on ISMR is understood, the influence of negative IOD (nIOD) on ISMR is not yet recognized. In this study, it is revealed that those opposite phases of IOD are associated with distinct regional asymmetries in rainfall anomalies. The pIOD is associated with a tripolar pattern in rainfall anomalies with above normal rainfall in central parts of India and below normal rainfall to north and south of it. Conversely, the nIOD is associated with a zonal dipole having above (below) normal rainfall on the western (eastern) half of the country. This spatial quasi-asymmetry arises from the differences in the atmospheric responses and the associated differences in moisture transports to the region during contrasting phases of the IOD.

Decadal climate predictability in the southern Indian Ocean captured by SINTEX-F using a simple SST-nudging scheme.

Decadal climate variability in the southern Indian Ocean has great influences on southern African climate through modulation of atmospheric circulation. Although many efforts have been made to understanding physical mechanisms, predictability of the decadal climate variability, in particular, the internally generated variability independent from external atmospheric forcing, remains poorly understood. This study investigates predictability of the decadal climate variability in the southern Indian Ocean using a coupled general circulation model, called SINTEX-F. The ensemble members of the decadal reforecast experiments were initialized with a simple sea surface temperature (SST) nudging scheme. The observed positive and negative peaks during late 1990s and late 2000s are well reproduced in the reforecast experiments initiated from 1994 and 1999, respectively. The experiments initiated from 1994 successfully capture warm SST and high sea level pressure anomalies propagating from the South Atlantic to the southern Indian Ocean. Also, the other experiments initiated from 1999 skillfully predict phase change from a positive to negative peak. These results suggest that the SST-nudging initialization has the essence to capture the predictability of the internally generated decadal climate variability in the southern Indian Ocean.

Climate Based Predictability of Oil Palm Tree Yield in Malaysia.

The influence of local conditions and remote climate modes on the interannual variability of oil palm fresh fruit bunches (FFB) total yields in Malaysia and two major regions (Peninsular Malaysia and Sabah/Sarawak) is explored. On a country scale, the state of sea-surface temperatures (SST) in the tropical Pacific Ocean during the previous boreal winter is found to influence the regional climate. When El Niño occurs in the Pacific Ocean, rainfall in Malaysia reduces but air temperature increases, generating a high level of water stress for palm trees. As a result, the yearly production of FFB becomes lower than that of a normal year since the water stress during the boreal spring has an important impact on the total annual yields of FFB. Conversely, La Niña sets favorable conditions for palm trees to produce more FFB by reducing chances of water stress risk. The region of the Leeuwin current also seems to play a secondary role through the Ningaloo Niño/ Niña in the interannual variability of FFB yields. Based on these findings, a linear model is constructed and its ability to reproduce the interannual signal is assessed. This model has shown some skills in predicting the total FFB yield.

Predicting El Niño Beyond 1-year Lead: Effect of the Western Hemisphere Warm Pool.

Due to the profound impact of El Niño-Southern Oscillation (ENSO) on global climate and weather, extensive research has been devoted to its prediction. However, prediction accuracy based on observation is still insufficient and largely limited to less than one year of lead time. In this study, we demonstrate the possibility that anomalous sea surface temperature (SST) warming (cooling) in the Western Hemisphere Warm Pool (WHWP, a.k.a. Atlantic Warm Pool) near the Intra-Americas Sea (IAS), which is the second largest warm pool on the planet, contributes to the initiation of La Niña (El Niño) with a 17-month lag time. SST anomalies in WHWP in late boreal summer contribute significantly to the emergence of the Pacific meridional mode (PMM) via interaction between the ocean and atmosphere over the subtropical North Pacific during the subsequent winter and spring. Near-equatorial surface wind anomalies associated with the PMM can further trigger ENSO through the dynamics of the equatorial oceanic waves. Thus, this observational analysis presents a clear step-by-step explanation about the influence of WHWP on ENSO development with a 17-month lead time.

Role of subsurface ocean in decadal climate predictability over the South Atlantic.

Decadal climate predictability in the South Atlantic is explored by performing reforecast experiments using a coupled general circulation model with two initialization schemes; one is assimilated with observed sea surface temperature (SST) only, and the other is additionally assimilated with observed subsurface ocean temperature and salinity. The South Atlantic is known to undergo decadal variability exhibiting a meridional dipole of SST anomalies through variations in the subtropical high and ocean heat transport. Decadal reforecast experiments in which only the model SST is initialized with the observation do not predict well the observed decadal SST variability in the South Atlantic, while the other experiments in which the model SST and subsurface ocean are initialized with the observation skillfully predict the observed decadal SST variability, particularly in the Southeast Atlantic. In-depth analysis of upper-ocean heat content reveals that a significant improvement of zonal heat transport in the Southeast Atlantic leads to skillful prediction of decadal SST variability there. These results demonstrate potential roles of subsurface ocean assimilation in the skillful prediction of decadal climate variability over the South Atlantic.

Seasonally lagged effects of climatic factors on malaria incidence in South Africa.

Globally, malaria cases have drastically dropped in recent years. However, a high incidence of malaria remains in some sub-Saharan African countries. South Africa is mostly malaria-free, but northeastern provinces continue to experience seasonal outbreaks. Here we investigate the association between malaria incidence and spatio-temporal climate variations in Limpopo. First, dominant spatial patterns in malaria incidence anomalies were identified using self-organizing maps. Composite analysis found significant associations among incidence anomalies and climate patterns. A high incidence of malaria during the pre-peak season (Sep-Nov) was associated with the climate phenomenon La Niña and cool air temperatures over southern Africa. There was also high precipitation over neighbouring countries two to six months prior to malaria incidence. During the peak season (Dec-Feb), high incidence was associated with positive phase of Indian Ocean Subtropical Dipole. Warm temperatures and high precipitation in neighbouring countries were also observed two months prior to increased malaria incidence. This lagged association between regional climate and malaria incidence suggests that in areas at high risk for malaria, such as Limpopo, management plans should consider not only local climate patterns but those of neighbouring countries as well. These findings highlight the need to strengthen cross-border control of malaria to minimize its spread.

Anatomy of Indian heatwaves.

India suffers from major heatwaves during March-June. The rising trend of number of intense heatwaves in recent decades has been vaguely attributed to global warming. Since the heat waves have a serious effect on human mortality, root causes of these heatwaves need to be clarified. Based on the observed patterns and statistical analyses of the maximum temperature variability, we identified two types of heatwaves. The first-type of heatwave over the north-central India is found to be associated with blocking over the North Atlantic. The blocking over North Atlantic results in a cyclonic anomaly west of North Africa at upper levels. The stretching of vorticity generates a Rossby wave source of anomalous Rossby waves near the entrance of the African Jet. The resulting quasi-stationary Rossby wave-train along the Jet has a positive phase over Indian subcontinent causing anomalous sinking motion and thereby heatwave conditions over India. On the other hand, the second-type of heatwave over the coastal eastern India is found to be due to the anomalous Matsuno-Gill response to the anomalous cooling in the Pacific. The Matsuno-Gill response is such that it generates northwesterly anomalies over the landmass reducing the land-sea breeze, resulting in heatwaves.

ENSO's far reaching connection to Indian cold waves.

During boreal winters, cold waves over India are primarily due to transport of cold air from higher latitudes. However, the processes associated with these cold waves are not yet clearly understood. Here by diagnosing a suite of datasets, we explore the mechanisms leading to the development and maintenance of these cold waves. Two types of cold waves are identified based on observed minimum surface temperature and statistical analysis. The first type (TYPE1), also the dominant one, depicts colder than normal temperatures covering most parts of the country while the second type (TYPE2) is more regional, with significant cold temperatures only noticeable over northwest India. Quite interestingly the first (second) type is associated with La Niña (El Niño) like conditions, suggesting that both phases of ENSO provide a favorable background for the occurrence of cold waves over India. During TYPE1 cold wave events, a low-level cyclonic anomaly generated over the Indian region as an atmospheric response to the equatorial convective anomalies is seen advecting cold temperatures into India and maintaining the cold waves. In TYPE2 cold waves, a cyclonic anomaly generated over west India anomalously brings cold winds to northwest India causing cold waves only in those parts.